Floating photovoltaic power station floating body transportation state detection method and system

By installing multiple sensors on the floating body of a floating photovoltaic power station and performing real-time data processing and multi-dimensional data fusion analysis, combined with adaptive algorithms and machine learning models, the shortcomings of floating body transportation status monitoring are solved, and more accurate and timely Risk assessment and early warning improve transportation safety and efficiency.

CN119063779APending Publication Date: 2024-12-03HUANENG POWER INT ENERGY DEV CO LTD
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202410979464.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing floating photovoltaic power station floating bodies lack a comprehensive and real-time status monitoring and early warning mechanism during transportation, making it difficult to cope with the complex maritime transportation environment. The data processing capacity of traditional monitoring methods is limited, and in-depth analysis and prediction cannot be carried out, which increases transportation risks. .

Method used

Install a variety of sensors at key structural points of the floating body, record initial data as reference values, collect and process data in real time, combine two-level thresholds for status evaluation, trigger intelligent early warning through a multi-level early warning mechanism, and integrate sensor data, environmental data and transportation routes. The information is carried out in a multi-dimensional data fusion analysis, and the monitoring parameters and machine learning models are adjusted using adaptive algorithms to predict potential state changes, and a comprehensive state report is generated.

Benefits of technology

Achieve comprehensive, real-time and intelligent monitoring of floating body status, improve transportation safety and efficiency, significantly improve data accuracy and reliability, enhance environmental adaptability and monitoring accuracy, possess forward-looking risk assessment capabilities, and improve early warning timeliness and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063779A_ABST
    Figure CN119063779A_ABST
Patent Text Reader

Abstract

The invention discloses a floating photovoltaic power station floating body transportation state detection method and system, and relates to the technical field of photovoltaic power generation, and the method comprises the steps: installing a plurality of sensors at key structure points of a floating body; continuously collecting data of each sensor according to a preset frequency; deviation is calculated, real-time state evaluation is carried out in combination with a dynamic threshold value, and intelligent early warning is triggered; performing multi-dimensional data fusion analysis, and evaluating potential risks based on a multi-dimensional analysis result; a comprehensive status report is generated and alarms and prompts are provided to operators. According to the invention, through comprehensive application of various sensors, comprehensive monitoring of the floating body state and environmental conditions is realized, and the accuracy and reliability of data are significantly improved. The achievement of the invention is supported by national key research and development plan projects, and the project name is offshore floating photovoltaic power generation key technology and core component research and development and engineering demonstration (project number: 2022YFB4200700).
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0002] The present invention relates to the technical field of photovoltaic power generation, and in particular to a method and system for detecting the transport status of a floating body of a floating photovoltaic power station. Background Art

[0003] As an emerging renewable energy solution, floating photovoltaic power stations have received widespread attention in recent years. Such power stations are usually built on reservoirs, lakes or the surface of the ocean, using floating bodies to support photovoltaic panels. However, large floating bodies face many challenges during transportation, such as structural stress, tilt and displacement, which may affect the integrity of the floating body and the efficiency of subsequent installation. At present, the monitoring of the transportation status of floating bodies mainly relies on simple displacement and inclination measurements, lacks a comprehensive and real-time status assessment and early warning mechanism, and is difficult to cope with the complex marine transportation environment. In addition, traditional monitoring methods have limited data processing capabilities, and cannot perform in-depth analysis and prediction, which increases transportation risks. Summary of the invention

[0004] In view of the problems existing in the existing method for detecting the transportation status of the floating body of a floating photovoltaic power station, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to achieve comprehensive, real-time and intelligent status monitoring of the floating body of a floating photovoltaic power station during transportation, so as to improve transportation safety and efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a method for detecting the transportation status of a floating body of a floating photovoltaic power station, which includes installing multiple sensors at key structural points of the floating body, and recording the initial data of each sensor when the floating body is in a stationary state as a reference value; during the transportation process, continuously collecting data from each sensor at a preset frequency and performing real-time processing; calculating the deviation between the sensor data after real-time processing and the reference value, combining two-level thresholds to perform real-time status evaluation, and triggering intelligent warnings through a multi-level warning mechanism; integrating the sensor data and status evaluation results after real-time processing, combining external environmental data and transportation route information, and performing multi-dimensional data fusion analysis; based on historical data and environmental conditions, using an adaptive algorithm to dynamically adjust the two-level thresholds of each monitoring parameter to adapt to different transportation stages and environmental conditions; based on the results of the multi-dimensional data fusion analysis, using a machine learning model to predict potential state changes of the floating body and evaluate potential risks; based on the monitoring parameters, status evaluation results and prediction results, generating a comprehensive status report to provide alarms and prompts to operators.

[0008] As a preferred solution of the method for detecting the transportation status of the floating body of the floating photovoltaic power station described in the present invention, wherein: installing multiple sensors at the key structural points of the floating body, and recording the initial data of each sensor when the floating body is in a static state as a reference value includes the following steps: determining the key structural points on the floating body, the key structural points include the four corners, the center point and the main force points of the floating body; installing displacement sensors at the four corners of the floating body, and measuring the three-dimensional displacement of the floating body through the displacement sensors; installing a dual-axis inclination sensor at the center of the top of the floating body, and measuring the pitch angle and roll angle of the floating body through the dual-axis inclination sensor; installing a three-axis acceleration sensor at the center of the floating body. The invention relates to a method for collecting floating body data and a floating body calibration system, wherein the method comprises the following steps: a sensor is installed at a main stress point of the floating body, and the linear acceleration and angular acceleration of the floating body are measured by the three-axis acceleration sensor; a strain sensor is installed at a main stress point of the floating body, and the local stress state is monitored by the strain sensor to generate strain data; all sensors are connected to a central data acquisition device through a signal line, and a unified timestamp mark is set; when the floating body is stationary and under preset environmental conditions, the data of each sensor is collected at a preset frequency; statistical analysis is performed on the collected sensor data, and the arithmetic mean value of each sensor data is calculated; the arithmetic mean value is used as a reference value of each sensor and stored in a calibration parameter database of the data acquisition system.

[0009] As a preferred solution of the method for detecting the transport status of the floating body of the floating photovoltaic power station described in the present invention, real-time processing includes the following steps: starting the data acquisition system to continuously collect data from each sensor during the entire transportation process; performing real-time inspection on the sensor data, identifying and marking abnormal values ​​and data breakpoints; using a low-pass filter to filter, zero-mean and standardize the acceleration and strain data to unify the data of different physical quantities into the same numerical range; and temporarily storing the acceleration and strain data after filtering, zero-mean and standardization in a local cache in chronological order.

[0010] As a preferred solution of the method for detecting the floating body transportation state of the floating photovoltaic power station of the present invention, the low-pass filter sets a suitable cut-off frequency and filter order according to actual needs, and the specific formula is as follows:

[0011]

[0012] Where s is a complex frequency variable, ω c is the cut-off frequency and n is the filter order.

[0013] As a preferred solution of the method for detecting the transport status of the floating body of the floating photovoltaic power station described in the present invention, the method comprises the following steps: extracting the preliminary status assessment report and historical data of the first time period from the system database and preprocessing them; using the sliding time window method, calculating the statistical characteristics of each monitoring parameter at different time scales, the monitoring parameters including displacement, inclination, acceleration and strain; based on the statistical characteristics, using the adaptive algorithm to calculate the dynamic baseline of each monitoring parameter; calculating a new two-level threshold according to the dynamic baseline and a predefined safety factor, the two-level threshold including a warning threshold and a danger threshold; making a secondary adjustment to the calculated two-level threshold according to the current transport stage and environmental conditions; comparing the adjusted two-level threshold with the original two-level threshold to determine the change range, and triggering the manual review mechanism if the change range exceeds the preset limit; updating the two-level threshold that has been reviewed or does not need to be reviewed to the system; recording the adjustment process and results of the two-level threshold, including the adjustment reason, adjustment range and review information, and storing them in the system log.

[0014] As a preferred solution of the method for detecting the floating transport state of a floating photovoltaic power station described in the present invention, the method comprises the following steps: using a machine learning model to predict potential state changes of a floating body comprises the following steps: extracting multidimensional analysis results, sensor data and environmental data within a first time period from a system database; preprocessing the multidimensional analysis results, sensor data and environmental data within the first time period; constructing and training a long short-term memory network model; inputting the multidimensional analysis results, sensor data and environmental data into the long short-term memory network model to predict key state parameters of the floating body; comparing the key state parameters of the floating body with the adjusted warning threshold or danger threshold, marking the time points and parameters exceeding the warning threshold or danger threshold; regularly calculating the error between the predicted key state parameters of the floating body and the actual observed value, and if the error exceeds the preset error threshold, triggering the retraining operation of the long short-term memory network model.

[0015] As a preferred solution of the method for detecting the floating transport status of a floating photovoltaic power station described in the present invention, generating a comprehensive status report to provide alarms and prompts to operators includes setting a graded alarm system according to the monitoring parameter deviation and the prediction result, specifically as follows: if the deviation between the real-time value and the reference value of all monitoring parameters is less than 1 / 2 of the warning threshold, and the prediction result shows that the parameter change amplitude within the first preset time period does not exceed 7 / 10 of the warning threshold, then a level 1 alarm is set, indicating a normal state, and routine monitoring and equipment inspection are performed at the first preset frequency; if the deviation between the real-time value and the reference value of any monitoring parameter reaches or exceeds 1 / 2 of the warning threshold but is less than 1, or the prediction result shows that the parameter change amplitude within the first preset time period exceeds 7 / 10 of the warning threshold but is less than 1, then a headphone alarm is set, indicating that a warning is needed. Attention, at this time, increase the monitoring frequency to the second preset frequency; if the deviation between the real-time value of any monitoring parameter and the baseline value reaches or exceeds the warning threshold but is less than the 4 / 5 danger threshold, or the forecast result shows that the parameter change range in the first preset time period exceeds the warning threshold but is less than the 4 / 5 danger threshold, then a third-level alarm is set, indicating that vigilance is needed. At this time, increase the monitoring frequency to the third preset frequency, and at the same time comprehensively check the equipment structure, adjust the route speed, and prepare emergency equipment; if the deviation between the real-time value of any monitoring parameter and the baseline value exceeds the 4 / 5 danger threshold, or the forecast result shows that the parameter change range in the first preset time period exceeds the 4 / 5 danger threshold, then a fourth-level alarm is set, indicating an emergency state. At this time, notify the relevant personnel immediately, assess whether to stop sailing, determine a safe haven, activate the emergency plan, and increase the monitoring and reporting frequency.

[0016] In the second aspect, an embodiment of the present invention provides a floating photovoltaic power station floating body transportation status detection system, which includes a sensor installation module, which is used to install multiple sensors at key structural points of the floating body, and record the initial data of each sensor in the static state of the floating body as a reference value; a data acquisition module, which is used to continuously collect the data of each sensor at a preset frequency during transportation and perform real-time processing; a data processing and evaluation module, which is used to calculate the deviation between the sensor data after real-time processing and the reference value, and perform real-time status evaluation in combination with two-level thresholds, and trigger intelligent early warning through a multi-level early warning mechanism; a multi-dimensional data fusion analysis module, which is used to integrate the sensor data and status evaluation results after real-time processing, and perform multi-dimensional data fusion analysis in combination with external environmental data and transportation route information; based on historical data and environmental conditions, an adaptive algorithm is used to dynamically adjust the two-level thresholds of each monitoring parameter to adapt to different transportation stages and environmental conditions; based on the multi-dimensional data fusion analysis results, a machine learning model is used to predict potential state changes of the floating body and evaluate potential risks; a comprehensive status report generation module is used to generate a comprehensive status report based on monitoring parameters, status evaluation results and prediction results to provide alarms and prompts to operators.

[0017] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the method for detecting the floating body transportation status of a floating photovoltaic power station as described in the first aspect of the present invention are implemented.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the method for detecting the floating body transportation status of a floating photovoltaic power station as described in the first aspect of the present invention are implemented.

[0019] The beneficial effects of the present invention are as follows: Through the comprehensive application of multiple sensors, the present invention realizes comprehensive monitoring of the floating body state and environmental conditions, significantly improving the accuracy and reliability of the data. By adopting technologies such as real-time processing and dynamic threshold adjustment, the system can automatically adjust the monitoring parameters according to different conditions, improving environmental adaptability and monitoring accuracy. The application of multi-level early warning mechanism and machine learning model enables the system to have forward-looking risk assessment capabilities, improving the timeliness and accuracy of early warning. Real-time data transmission and remote monitoring functions enable the expert team to grasp the floating body state at any time, improving decision-making efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 The framework flow chart of the method for detecting the floating body transportation status of a floating photovoltaic power station.

[0022] Figure 2 The present invention is a flow chart of sensor installation for a method for detecting the floating body transportation status of a floating photovoltaic power station.

[0023] Figure 3 A diagram of computer equipment for a method for detecting the transport status of a floating body of a floating photovoltaic power station. DETAILED DESCRIPTION

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0025] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0026] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0027] Example 1

[0028] Reference Figure 1 to Figure 3 , which is the first embodiment of the present invention, and provides a method for detecting the transportation status of a floating body of a floating photovoltaic power station, comprising:

[0029] S1: Install a variety of sensors at key structural points of the floating body, and record the initial data of each sensor when the floating body is in a static state as the baseline value.

[0030] Preferably, key structural points on the float are determined, including the four corners, the center point and the main stress points of the float; displacement sensors are installed at the four corners of the float to measure the three-dimensional displacement of the float; a two-axis inclination sensor is installed at the center of the top of the float to measure the pitch angle and roll angle of the float; a three-axis acceleration sensor is installed at the center of the float to measure the linear acceleration and angular acceleration of the float; strain sensors are installed at the main stress points to monitor the local stress state; all sensors are connected to the central data acquisition device through signal lines, and a unified timestamp mark is set to ensure data synchronization; when the float is stationary and under preset environmental conditions, the data of each sensor is collected at a preset frequency for a duration of not less than 30 minutes; the collected static data is preprocessed and statistically analyzed, including removing outliers and calculating the arithmetic mean of the data of each sensor; the calculated arithmetic mean is used as the reference value of each sensor and stored in the calibration parameter database of the data acquisition system.

[0031] In addition, a shipboard weather station is installed to obtain real-time environmental data, including wind speed, wind direction, temperature, humidity and air pressure. At the same time, satellite communication equipment is configured for data transmission and communication with the remote monitoring center. To ensure the reliability of the system, key sensors and data processing equipment are redundantly configured. The entire monitoring system is powered by independent solar panels and battery packs to ensure continuous operation during long-distance transportation.

[0032] It should be noted that, in the present invention, the preset environmental conditions refer to an ambient temperature of 20±2°C, a humidity of 50±5%, and a wind speed of less than 0.5 m / s. The preset frequencies are: displacement and inclination sensors are sampled at 1 Hz, and acceleration and strain sensors are sampled at 100 Hz.

[0033] S2: During the transportation process, the sensor data is continuously collected at a preset frequency, and processed and stored in real time.

[0034] Specifically, the following steps are included:

[0035] S2.1: Start the data acquisition system and continuously collect data from each sensor during the entire transportation process.

[0036] It should be noted that under normal circumstances, the displacement and inclination sensors are sampled at 0.1Hz, and the acceleration and strain sensors are sampled at 10Hz. When an abnormality is detected or the alarm state is yellow or above, the sampling frequency is automatically increased to the preset frequency set in S1.

[0037] S2.2: Perform real-time inspection of the collected raw data to identify and mark obvious outliers and data breakpoints.

[0038] Specifically, for abnormal values, interpolation or the nearest valid value is used as replacement; for data breakpoints, the breakpoint time and duration are recorded.

[0039] S2.3: Filter the acceleration and strain data using a low-pass filter to remove high-frequency noise.

[0040] Specifically, use the Butterworth low-pass filter and set the appropriate cutoff frequency and filter order according to actual needs. The specific formula is as follows:

[0041]

[0042] Where s is a complex frequency variable, ω c is the cut-off frequency and n is the filter order.

[0043] S2.4: Perform zero-mean processing on the filtered data to eliminate the influence of sensor zero drift.

[0044] S2.5: Standardize the processed data to unify the data of different physical quantities into the same numerical range.

[0045] S2.6: The standardized data is temporarily stored in a local cache in chronological order, and the processed data is checked for integrity at preset time intervals (eg, 10 minutes).

[0046] S2.7: The processed data shall be transmitted to the remote monitoring center via satellite communication equipment every hour.

[0047] S3: Calculate the deviation between the processed data and the baseline value, perform real-time status assessment based on dynamic thresholds, and trigger intelligent warnings through a multi-level warning mechanism.

[0048] Specifically, the following steps are included:

[0049] S3.1: Retrieve the reference value of each sensor from the calibration parameter database, and read the displacement, inclination, acceleration and strain data after filtering and standardization.

[0050] S3.2: Regularly compare the baseline value with the currently processed data to obtain the deviation of each monitoring parameter, including displacement deviation, inclination deviation, acceleration deviation and strain deviation.

[0051] S3.3: According to the structural characteristics of the floating body and transportation requirements, two-level thresholds are set for each monitoring parameter, including warning threshold and danger threshold.

[0052] S3.4: Compare the calculated deviation value with the two-level threshold value, and trigger a warning signal of a corresponding level according to the comparison result.

[0053] S3.5: Generate a preliminary status assessment report based on the deviation values, warning levels and historical trends of each monitoring parameter.

[0054] It should be noted that the preliminary status assessment report includes the current value and deviation value of each monitoring parameter, parameter status (normal, warning, dangerous), triggered alarm signals (if any), and parameter change trend analysis.

[0055] S3.6: Store the preliminary status assessment report and alarm signals in the system database to provide a basis for subsequent analysis and decision-making.

[0056] S4: Integrate the processed sensor data and status assessment results, combine them with external environment data and transportation route information, and conduct multi-dimensional data fusion analysis.

[0057] Specifically, collect and organize multi-source data including processed sensor data (displacement, inclination, acceleration, strain), status assessment results (preliminary status assessment report), external environment data (meteorological data, sea condition information), and transportation route information (GPS positioning, speed, heading); synchronize time and space for data from different sources to ensure data consistency; use data fusion algorithm to fuse multi-source data to generate comprehensive state estimation; construct a multi-dimensional analysis model including structural mechanics sub-model, dynamics sub-model and environmental impact sub-model, the structural mechanics sub-model is used to analyze the stress condition and deformation of the floating body, the dynamics sub-model is used to evaluate the motion characteristics and stability of the floating body, and the environmental impact sub-model is used to analyze the impact of the external environment on the state of the floating body; based on the fused data, use the multi-dimensional analysis model for comprehensive analysis to obtain an overall status assessment of the floating body; use the time series analysis method to identify the long-term change trend of the floating body state, generate a multi-dimensional data fusion analysis report, and store it in the system database; transmit a complete multi-dimensional data fusion analysis report to the remote monitoring center every 6 hours, and increase the transmission frequency in abnormal or alarm conditions.

[0058] It should be noted that the structural mechanics sub-model includes force analysis ∑F and deformation analysis σ. The specific formula is as follows:

[0059] ∑F=m·a

[0060] σ=E·χ

[0061] Among them, ∑F is the resultant force, m is the mass, a is the acceleration, σ is the stress, E is the Young's modulus, and χ is the strain.

[0062] It should be noted that the dynamics sub-model includes stability analysis, and the specific formula is as follows:

[0063] ΣM=I·α

[0064] Among them, ΣM is the resultant torque, I is the moment of inertia, and α is the angular velocity.

[0065] It should be noted that the environmental impact sub-model includes environmental force impact analysis, and the specific formula is as follows:

[0066] F environment =ρ·A·C d ·v 2

[0067] Where ρ is the fluid density, A is the windward area, C d is the drag coefficient and v is the velocity.

[0068] S5: Based on historical data and environmental conditions, an adaptive algorithm is used to dynamically adjust the two-level thresholds of each monitoring parameter to adapt to different transportation stages and environmental conditions.

[0069] Specifically, the preliminary status assessment report and historical data of the first time period (such as the past 24 hours) are extracted from the system database, and preprocessed, including data cleaning, normalization and time series alignment; the sliding time window method is used to calculate the statistical characteristics of each monitoring parameter at different time scales, such as the mean, standard deviation, maximum value and minimum value; based on the calculated statistical characteristics, the dynamic baseline of each monitoring parameter is calculated using an adaptive algorithm (such as the exponential weighted moving average method); according to the dynamic baseline and the predefined safety factor, a new two-level threshold is calculated, including a warning threshold and a danger threshold; according to the current transportation stage and environmental conditions (such as weather conditions, sea conditions, etc.), the calculated two-level threshold is adjusted for the second time; the adjusted two-level threshold is compared with the original two-level threshold to determine the change range, and if the change range exceeds the preset limit, the manual review mechanism is triggered; the two-level threshold that has been reviewed or does not need to be reviewed is updated to the system for subsequent status monitoring and alarm judgment; the adjustment process and results of the two-level threshold, including the adjustment reason, adjustment range and review information (if any), are recorded and stored in the system log; the updated two-level threshold is applied to the real-time status assessment process of S3.

[0070] It should be noted that a manual intervention mechanism is set up. When the threshold value changes beyond the preset limit, the experts in the remote monitoring center are notified through the satellite communication system for review. The experts can view the detailed data through the remote connection and make a decision within 30 minutes whether to accept the new threshold value.

[0071] S6: Based on the results of multi-dimensional analysis, a machine learning model is used to predict the possible state changes of the floating body in the short term and assess potential risks.

[0072] Specifically, extract the multidimensional analysis results, sensor data and environmental data within a first time period (such as the past week) from the system database; preprocess the extracted data, including missing value filling, outlier deletion and data standardization, and divide it into a training set and a validation set according to a preset ratio; construct a long short-term memory network LSTM model, set the number of input layer, hidden layer and output layer nodes, and set an appropriate learning rate, batch size and number of iterations, wherein the number of input layer nodes is the same as the number of features, the hidden layer has 100 nodes, and the number of output layer nodes is the same as the number of prediction parameters (the present invention has 4 nodes, corresponding to displacement, inclination, acceleration and strain); use training The LSTM model is trained on the data of the set, and the model performance is evaluated on the validation set. If the performance on the validation set does not meet the standard, the hyperparameters are adjusted and retrained; the multi-dimensional analysis results, sensor data and environmental data are input into the long short-term memory network model to predict the key state parameters of the floating body, including the displacement, inclination, acceleration and strain value of the floating body; the predicted key state parameters of the floating body are compared with the adjusted warning threshold or danger threshold, and the time points and parameters exceeding the warning threshold or danger threshold are marked; the error between the predicted key state parameters of the floating body and the actual observed value is calculated regularly, and if the error exceeds the preset error threshold, the long short-term memory network model retraining operation is triggered.

[0073] S7: Generates comprehensive status reports and provides alerts and prompts to operators based on real-time monitoring data, status assessment results, dynamic thresholds, and prediction results.

[0074] It should be noted that the comprehensive status report includes the real-time value and deviation value of each current monitoring parameter, parameter status (normal, warning, dangerous), triggered alarm signal (if any), parameter change trend analysis, predicted parameter changes in the next 24 hours, and potential risk assessment results.

[0075] Furthermore, a graded alarm system is set up according to the monitoring parameter deviation and the prediction result: if the deviation between the real-time value and the baseline value of all monitoring parameters is less than 1 / 2 of the warning threshold, and the prediction result shows that the parameter change amplitude in the first preset time period does not exceed 7 / 10 of the warning threshold, a first-level alarm is set, indicating a normal state, and routine monitoring and equipment inspection are performed at the first preset frequency; if the deviation between the real-time value and the baseline value of any monitoring parameter reaches or exceeds 1 / 2 of the warning threshold but is less than 1, or the prediction result shows that the parameter change amplitude in the first preset time period exceeds 7 / 10 of the warning threshold but is less than 1, an earphone alarm is set, indicating that attention is needed, and the monitoring frequency is increased to the second preset frequency; if the real-time value of any monitoring parameter If the deviation between the real-time value and the benchmark value reaches or exceeds the warning threshold but is less than the 4 / 5 danger threshold, or the forecast result shows that the parameter change range within the first preset time period exceeds the warning threshold but is less than the 4 / 5 danger threshold, a level 3 alarm is set, indicating that vigilance is required. At this time, the monitoring frequency is increased to the third preset frequency, and the equipment structure is comprehensively checked, the route speed is adjusted, and emergency equipment is prepared; if the deviation between the real-time value and the benchmark value of any monitoring parameter exceeds the 4 / 5 danger threshold, or the forecast result shows that the parameter change range within the first preset time period exceeds the 4 / 5 danger threshold, a level 4 alarm is set, indicating an emergency state. At this time, relevant personnel are notified immediately to assess whether to stop sailing, determine a safe haven, activate the emergency plan, and increase the monitoring and reporting frequency.

[0076] It should be noted that the first preset time period can be 24 hours, 48 ​​hours or other appropriate time lengths, which can be set according to factors such as the length of the transportation route and the reliability of the weather forecast, and the present invention does not limit this. The first preset frequency, the second preset frequency, and the third preset frequency are decreasing in time, the first preset frequency can be once every hour, the second preset frequency can be once every 30 minutes, and the third preset frequency can be once every 10 minutes.

[0077] Furthermore, according to the determined alarm level, alarms and prompts are sent to the on-site operators through the shipboard display system, and alarm information and comprehensive status reports are sent to the remote monitoring center through the satellite communication system. The operator's response to the alarm and prompt is recorded, and the operator's feedback is collected to optimize the alarm and prompt mechanism. The generated comprehensive status report, alarm record and response measures are stored in the system database, and a unique time mark and serial number are added to each report to facilitate subsequent query and analysis.

[0078] Furthermore, the present embodiment also provides a floating photovoltaic power station floating body transportation state detection system, including a sensor installation module, which is used to install multiple sensors at key structural points of the floating body, and record the initial data of each sensor in the static state of the floating body as a reference value; a data acquisition module, which is used to continuously collect the data of each sensor at a preset frequency during transportation and perform real-time processing; a data processing and evaluation module, which is used to calculate the deviation between the sensor data after real-time processing and the reference value, and perform real-time state evaluation in combination with two-level thresholds, and trigger intelligent early warning through a multi-level early warning mechanism; a multi-dimensional data fusion analysis module, which is used to integrate the sensor data and state evaluation results after real-time processing, and perform multi-dimensional data fusion analysis in combination with external environmental data and transportation route information; based on historical data and environmental conditions, the two-level thresholds of each monitoring parameter are dynamically adjusted using an adaptive algorithm to adapt to different transportation stages and environmental conditions; based on the multi-dimensional data fusion analysis results, a machine learning model is used to predict potential state changes of the floating body and evaluate potential risks; a comprehensive status report generation module is used to generate a comprehensive status report based on monitoring parameters, status evaluation results and prediction results to provide alarms and prompts to operators.

[0079] This embodiment also provides a computer device, which is suitable for the case of a method for detecting the floating body transportation status of a floating photovoltaic power station, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the method for detecting the floating body transportation status of a floating photovoltaic power station proposed in the above embodiment.

[0080] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0081] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for detecting the transport status of a floating body of a floating photovoltaic power station as proposed in the above embodiment is implemented.

[0082] In summary, the present invention realizes comprehensive monitoring of the state of the floating body and environmental conditions through the comprehensive application of multiple sensors, significantly improving the accuracy and reliability of the data. By adopting technologies such as real-time processing and dynamic threshold adjustment, the system can automatically adjust the monitoring parameters according to different conditions, improving environmental adaptability and monitoring accuracy. The application of multi-level early warning mechanism and machine learning model enables the system to have forward-looking risk assessment capabilities, improving the timeliness and accuracy of early warning. Real-time data transmission and remote monitoring functions enable the expert team to grasp the state of the floating body at any time, improving decision-making efficiency and accuracy.

[0083] Example 2

[0084] Reference Figure 1 to Figure 3 , which is the second embodiment of the present invention, and this embodiment provides a method for detecting the floating body transportation status of a floating photovoltaic power station. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0085] Specifically, this simulation experiment tested the monitoring system of a large floating structure during maritime transportation. The experiment was divided into three stages: initial setup and static testing, transportation monitoring under normal sea conditions, and monitoring under severe weather conditions. The floating structure used in the experiment was 100 meters long, 30 meters wide, and 15 meters high, and was equipped with a variety of sensors, including displacement sensors, inclination sensors, acceleration sensors, and strain sensors.

[0086] The initial static test phase was conducted for 30 minutes of data collection under the environmental conditions of temperature 21°C, humidity 48%, and wind speed 0.3m / s. The test results showed that the baseline values ​​of all sensors were within the expected range, providing a reliable reference standard for subsequent monitoring. The baseline value of the displacement sensor was (0.00mm, 0.00mm, 0.00mm), the baseline value of the inclination sensor was 0.02° for pitch angle and 0.01° for roll angle, and the baseline value of the acceleration sensor was (0.00m / s 2 , 0.00m / s 2 , 9.81m / s 2 ), while the reference value of the strain sensor is 0 microstrain.

[0087] The transport monitoring phase under normal sea conditions simulated a 72-hour sea transport process. During this period, the buoy sailed at an average speed of 12 knots, the sea conditions were relatively stable, and the wave height was between 0.5 meters and 1.2 meters. The monitoring results showed that the changes in all parameters were within an acceptable range. The maximum deviation recorded by the displacement sensor was (±15mm, ±10mm, ±25mm), the maximum pitch angle recorded by the inclination sensor was 1.5°, and the maximum roll angle was 1.2°. The maximum value of the acceleration sensor is (±0.8m / s 2,±0.6m / s 2 ,10.2m / s 2 ), while the maximum strain recorded by the strain sensor was 150 microstrain. During this phase, the system remained in green alarm status throughout, and routine monitoring and equipment inspections were performed at a preset frequency.

[0088] The final stage of the experiment simulated severe weather conditions for 12 hours, with wind speeds reaching 20-25m / s and wave heights of 4-6 meters. Under these extreme conditions, the monitoring system showed good responsiveness. The maximum deviation recorded by the displacement sensor increased sharply to (±120mm, ±80mm, ±200mm), and the maximum pitch and roll angles recorded by the inclination sensor reached 5.8° and 4.9° respectively. The maximum value of the acceleration sensor rose to (±3.5m / s 2 ,±2.8m / s 2 ,12.5m / s 2 ), the maximum strain recorded by the strain sensor reached 580 microstrain. As the parameters change, the system gradually increases the alarm level from yellow alarm to orange alarm and finally to red alarm. Each alarm level is accompanied by corresponding response measures, including increasing the monitoring frequency, conducting equipment inspections, adjusting the speed and route, and finally deciding to temporarily stop sailing and find a safe haven.

[0089] Preferably, the comparison indicators of the present invention and the traditional method are shown in Table 1.

[0090] Table 1 Comparison index table of the present invention and the traditional method

[0091]

[0092]

[0093] Preferably, as shown in Table 1, the present invention is superior to traditional methods in multiple key indicators. The parameters monitored by the present invention are more comprehensive, including not only displacement and inclination, but also acceleration and strain monitoring, providing more comprehensive floating body status information. In terms of sampling frequency, the present invention adopts an adaptive method, which can be adjusted between 0.1-100Hz, which is more flexible than the fixed 1Hz sampling rate of the traditional method. The threshold setting adopts a dynamic adaptive method, which can better adapt to different environments and transportation stages. The early warning mechanism has been upgraded from the traditional single level to a four-level warning of green, yellow, orange and red, which is more precise and effective.

[0094] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting the transport status of a floating body of a floating photovoltaic power station, characterized in that: include, Install a variety of sensors at key structural points of the floating body, and record the initial data of each sensor when the floating body is in a static state as the baseline value; During transportation, the data from each sensor is continuously collected at a preset frequency and processed in real time; Calculate the deviation between the sensor data after real-time processing and the reference value, perform real-time status evaluation in combination with two-level thresholds, and trigger intelligent warning through a multi-level warning mechanism; Integrate the sensor data and status assessment results after real-time processing, combine with external environment data and transportation route information, and conduct multi-dimensional data fusion analysis; Based on historical data and environmental conditions, an adaptive algorithm is used to dynamically adjust the two-level thresholds of each monitoring parameter to adapt to different transportation stages and environmental conditions; Based on the results of multi-dimensional data fusion analysis, machine learning models are used to predict potential state changes of floating bodies and assess potential risks; Based on monitoring parameters, status assessment results and prediction results, comprehensive status reports are generated to provide alarms and prompts to operators.

2. The method for detecting the transport status of a floating body of a floating photovoltaic power station according to claim 1, characterized in that: The method of installing a plurality of sensors at key structural points of the floating body and recording the initial data of each sensor when the floating body is in a static state as a reference value comprises the following steps: Determine the key structural points on the floating body, wherein the key structural points include the four corners, the center point and the main stress points of the floating body; Displacement sensors are installed at the four corners of the floating body to measure the three-dimensional displacement of the floating body through the displacement sensors; A dual-axis tilt sensor is installed at the center of the top of the floating body, and the pitch angle and roll angle of the floating body are measured by the dual-axis tilt sensor; A triaxial acceleration sensor is installed at the center of the floating body, and the linear acceleration and angular acceleration of the floating body are measured by the triaxial acceleration sensor; Install strain sensors at the main stress points of the floating body, monitor the local stress state through the strain sensors, and generate strain data; Connect all sensors to the central data collector through signal lines and set a unified timestamp; When the floating body is stationary and in preset environmental conditions, data from each sensor is collected at a preset frequency; Perform statistical analysis on the collected sensor data and calculate the arithmetic mean of each sensor data; The arithmetic mean value is used as the reference value of each sensor and stored in the calibration parameter database of the data acquisition system.

3. The method for detecting the transport status of a floating body of a floating photovoltaic power station according to claim 1, characterized in that: The real-time processing comprises the following steps: Start the data collection system to continuously collect data from various sensors during the entire transportation process; Performing real-time inspection of the sensor data to identify and mark outliers and data breakpoints; Use a low-pass filter to filter, zero-mean and standardize the acceleration and strain data to unify the data of different physical quantities into the same numerical range; The acceleration and strain data after filtering, zero-meaning and standardization are temporarily stored in a local cache in chronological order.

4. The method for detecting the transport status of a floating body of a floating photovoltaic power station according to claim 3, characterized in that: The low-pass filter sets a suitable cutoff frequency and filter order according to actual needs. The specific formula is as follows: Where s is a complex frequency variable, ω c is the cut-off frequency and n is the filter order.

5. The method for detecting the transport status of a floating body of a floating photovoltaic power station according to claim 1, characterized in that: The method of dynamically adjusting the two-level thresholds of each monitoring parameter using an adaptive algorithm comprises the following steps: Extracting the preliminary status assessment report and historical data of the first time period from the system database and performing preprocessing; Using a sliding time window method, the statistical characteristics of each monitoring parameter at different time scales are calculated, and the monitoring parameters include displacement, inclination, acceleration and strain; Based on the statistical characteristics, a dynamic baseline of each monitoring parameter is calculated using an adaptive algorithm; Calculating new two-level thresholds according to the dynamic baseline and a predefined safety factor, wherein the two-level thresholds include a warning threshold and a danger threshold; According to the current transportation stage and environmental conditions, the calculated two-level thresholds are adjusted twice; Compare the adjusted two-level thresholds with the original two-level thresholds to determine the magnitude of the change. If the magnitude of the change exceeds the preset limit, the manual review mechanism is triggered; Update the system with two levels of thresholds of either being reviewed or not being reviewed; Record the adjustment process and results of the two-level thresholds, including the reasons for adjustment, adjustment range and audit information, and store them in the system log.

6. The method for detecting the transport status of a floating body of a floating photovoltaic power station according to claim 1, characterized in that: The method of using a machine learning model to predict the potential state change of a floating body comprises the following steps: extracting multi-dimensional analysis results, sensor data, and environmental data within a first time period from a system database; Preprocessing the multi-dimensional analysis results, sensor data, and environmental data within the first time period; Build and train long short-term memory network models; Inputting multi-dimensional analysis results, sensor data and environmental data into the long short-term memory network model to predict key state parameters of the floating body; Comparing the key state parameters of the floating body with the adjusted warning threshold or danger threshold, marking the time point and parameters exceeding the warning threshold or danger threshold; The error between the predicted key state parameters of the floating body and the actual observed value is calculated regularly. If the error exceeds the preset error threshold, the long short-term memory network model retraining operation is triggered.

7. The method for detecting the transport status of a floating body of a floating photovoltaic power station according to claim 1, characterized in that: Generating a comprehensive status report to provide alarms and prompts to operators includes setting up a hierarchical alarm system based on monitoring parameter deviations and prediction results, as follows: If the deviation between the real-time value and the reference value of all monitoring parameters is less than 1 / 2 of the warning threshold, and the forecast result shows that the parameter change amplitude within the first preset time period does not exceed 7 / 10 of the warning threshold, a first-level alarm is set, indicating a normal state, and routine monitoring and equipment inspection are performed at the first preset frequency; If the deviation between the real-time value of any monitoring parameter and the reference value reaches or exceeds the 1 / 2 warning threshold but is less than 1, or the prediction result shows that the parameter change amplitude in the first preset time period exceeds the 7 / 10 warning threshold but is less than 1, an earphone alarm is set to indicate that attention is needed, and the monitoring frequency is increased to the second preset frequency; If the deviation between the real-time value of any monitoring parameter and the reference value reaches or exceeds the warning threshold but is less than 4 / 5 of the danger threshold, or the forecast result shows that the parameter change amplitude in the first preset time period exceeds the warning threshold but is less than 4 / 5 of the danger threshold, then a third-level alarm is triggered, indicating that vigilance is required. At this time, the monitoring frequency is increased to the third preset frequency, and the equipment structure is comprehensively checked, the route speed is adjusted, and emergency equipment is prepared; If the deviation between the real-time value of any monitoring parameter and the baseline value exceeds the 4 / 5 danger threshold, or the forecast result shows that the parameter change within the first preset time period exceeds the 4 / 5 danger threshold, a level 4 alarm is set, indicating an emergency state. At this time, relevant personnel are immediately notified to assess whether to stop sailing, determine a safe haven, activate the emergency plan, and increase monitoring and reporting frequency.

8. A floating photovoltaic power station floating body transportation state detection system, based on the floating photovoltaic power station floating body transportation state detection method according to any one of claims 1 to 7, characterized in that: Also includes, The sensor installation module is used to install a variety of sensors at key structural points of the floating body and record the initial data of each sensor when the floating body is in a static state as a reference value; The data acquisition module is used to continuously collect data from various sensors at a preset frequency during transportation and perform real-time processing; A data processing and evaluation module, which is used to calculate the deviation between the sensor data after real-time processing and the reference value, perform real-time status evaluation in combination with two-level thresholds, and trigger intelligent warnings through a multi-level warning mechanism; A multi-dimensional data fusion analysis module is used to integrate the sensor data and status assessment results after real-time processing, and combine the external environment data and transportation route information to perform multi-dimensional data fusion analysis; Based on historical data and environmental conditions, an adaptive algorithm is used to dynamically adjust the two-level thresholds of each monitoring parameter to adapt to different transportation stages and environmental conditions; Based on the results of multi-dimensional data fusion analysis, machine learning models are used to predict potential state changes of floating bodies and assess potential risks; The comprehensive status report generation module is used to generate a comprehensive status report based on monitoring parameters, status assessment results and prediction results to provide alarms and prompts to operators.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for detecting the floating body transportation state of a floating photovoltaic power station according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting the transport status of a floating body of a floating photovoltaic power station according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • House safety monitoring method and system based on machine learning

    CN119533582A

  • Stiff skeleton real-time monitoring method and system

    CN120593841A

  • Intelligent monitoring method and device for photovoltaic power station

    CN120710234A