Net cage ship fault early warning system

Abstract

The invention relates to the technical field of fault early warning, in particular to a net cage ship fault early warning system. Comprising an acquisition unit used for acquiring operation data of each acquisition point of a net cage ship and a data transmission unit connected with the acquisition unit and used for converting the operation data into communication signals and transmitting the communication signals to a monitoring center. The data processing module is connected with the data acquisition module and comprises a preprocessing unit for preprocessing the communication signal to output normalized data; the early warning module is connected with the data processing module and used for giving out fault early warning according to the analysis result; and the control module is respectively connected with the data acquisition module, the data processing module and the early warning module, and is used for determining the change rate of adjacent acquisition points according to the false alarm rate of fault early warning. According to the invention, the accuracy of fault early warning is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault warning, and in particular to a cage vessel fault warning system. Background Art

[0002] In the existing technology, as the aquaculture industry develops into the deep sea, the application of cage vessels is becoming more and more extensive. During the aquaculture process, cage vessels face a complex marine environment and various potential risks, such as equipment failure and bad weather. These factors may cause aquaculture losses or even casualties. In order to ensure the safe operation of cage vessels and the smooth progress of aquaculture production, improve the intelligence level of aquaculture platforms, and reduce the difficulty of aquaculture platform management, an effective fault warning system is needed to monitor the status of cage vessels in real time, detect potential faults in advance, and take timely measures.

[0003] Chinese Patent Publication No. CN118230517A discloses a ship fault warning and positioning system, comprising a data processing module, which is connected to a ship positioning module, a fault diagnosis module, a system management module, a backend database module, and an environmental monitoring module. The fault diagnosis module is also connected to a real-time monitoring module and an equipment positioning module. The system management module is also connected to a backend data module, a warning and alarm module, and a user operation module. The system is simple and easy to operate, capable of sending an alarm signal to the user operating terminal simultaneously with the ship's alarm device, allowing for rapid and timely response to the type of alarm. Positioning information is rapidly fed back via Beidou satellites and ship locators. It can also generate alarms not only for ship equipment failures but also for deviations from the ship's route and sudden emergencies. It can also monitor the ship's surrounding environment in real time, allowing for timely avoidance of hazardous routes.

[0004] It can be seen that the existing technology has the following problems: when faced with a large amount of real-time data, the computing resources of the data processing module may be insufficient, resulting in untimely or incomplete data processing, affecting the accuracy and timeliness of fault warning. Summary of the Invention

[0005] To this end, the present invention provides a cage vessel fault warning system to overcome the problem in the prior art that when faced with a large amount of real-time data, the computing resources of the data processing module may be insufficient, resulting in untimely or incomplete data processing, affecting the accuracy and timeliness of fault warning.

[0006] To achieve the above object, the present invention provides a cage vessel fault early warning system, comprising: The data acquisition module includes a collection unit for collecting operating data of each collection point of the cage vessel and a data transmission unit connected to the collection unit for converting the operating data into a communication signal and transmitting the signal to the monitoring center; a data processing module connected to the data acquisition module, comprising a preprocessing unit for preprocessing the communication signal to output normalized data, and a data analysis unit connected to the preprocessing unit for performing early warning analysis on the normalized data using a neural network model to output analysis results; an early warning module, connected to the data processing module, for issuing a fault early warning based on the analysis result; A control module is respectively connected to the data acquisition module, the data processing module and the early warning module, and is used to determine the change rate of adjacent acquisition points based on the false alarm rate of the fault early warning, or to determine the training enhancement ratio of missing data in the neural network model based on the byte missing rate of the normalized data, and to determine the operating data fusion threshold of different acquisition points based on the signal-to-noise ratio of the communication signal.

[0007] Furthermore, the control module is used to determine whether the accuracy of the fault warning meets the requirements based on the false alarm rate of the fault warning. If the false alarm rate of the fault warning is greater than a preset first false alarm rate, it is determined that the accuracy of the fault warning does not meet the requirements.

[0008] Furthermore, the control module is used to preliminarily determine that the effectiveness of the warning analysis does not meet the requirements when the false alarm rate of the fault warning is greater than the preset first false alarm rate and less than or equal to the preset second false alarm rate, and determine whether the effectiveness of the warning analysis meets the requirements based on the byte missing rate of the normalized data.

[0009] Furthermore, the control module is configured to increase the rate of change of adjacent collection points when the false alarm rate of the fault warning is greater than the preset second false alarm rate; The increase range of the change rate of adjacent collection points is determined by the difference between the false alarm rate of the fault warning and a preset second false alarm rate.

[0010] Furthermore, the control module is used to determine whether the effectiveness of the early warning analysis meets the requirements based on the byte missing rate of the normalized data. If the byte missing rate of the normalized data is greater than a preset first missing rate, it is determined that the effectiveness of the early warning analysis does not meet the requirements.

[0011] Furthermore, the control module is used to increase the training enhancement ratio of missing data in the neural network model when the byte missing rate of the normalized data is greater than the preset first missing rate and less than or equal to the preset second missing rate.

[0012] Furthermore, the control module is used to preliminarily determine that the transmission stability of the operating data does not meet the requirements when the byte loss rate of the normalized data is greater than the preset second loss rate, and determine whether the transmission stability of the operating data meets the requirements based on the signal-to-noise ratio of the communication signal.

[0013] Furthermore, the increase in the training enhancement ratio of missing data in the neural network model is determined by the difference between the byte missing rate of the normalized data and a preset first missing rate.

[0014] Furthermore, the control module is used to determine whether the transmission stability of the operating data meets the requirements based on the signal-to-noise ratio of the communication signal. If the signal-to-noise ratio of the communication signal is less than a preset signal-to-noise ratio, it is determined that the transmission stability of the operating data does not meet the requirements, and the operating data fusion threshold of different collection points is increased.

[0015] Furthermore, the increase range of the operation data fusion threshold of different collection points is determined by the difference between a preset signal-to-noise ratio and a signal-to-noise ratio of the communication signal.

[0016] Compared with the prior art, the beneficial effect of the present invention is that the system of the present invention adjusts the change rate of adjacent collection points according to the false alarm rate of fault warning by setting a data acquisition module, a data processing module, an early warning module and a control module. Due to the vibration of the equipment, some components may undergo slight displacement, causing the originally normal connection, gap and other parameters to change. The sensors monitoring these parameters will detect the numerical changes. The system cannot accurately distinguish whether it is normal component wear or temporary displacement caused by vibration, and may mistakenly judge it as a component failure and issue an early warning. By increasing the change rate of adjacent collection points, high change rate signals in a short period of time can be ignored, and only an alarm is given for displacements that exceed the limit for a long time, thereby avoiding misjudgment. The training enhancement ratio of missing data in the neural network model is adjusted according to the byte missing rate of normalized data. Since the data of some monitoring points in the data set are not uploaded in time or the data of certain periods are blank due to equipment failure, the analysis results will be biased and unable to fully and accurately reflect the actual situation, affecting The impact on model training and result accuracy may not accurately describe the rules behind the data, resulting in inaccurate warning results. By increasing the training enhancement ratio of missing data in the neural network model, the model can have more opportunities to learn samples containing missing data, so as to better adapt to the situation of missing data, improve the model's ability to process missing data, and reduce the deviation caused by missing data. The operating data fusion threshold of different collection points is adjusted according to the signal-to-noise ratio of the communication signal. Since there may be various electromagnetic interference sources around the cage ship, such as the generator on the ship is installed too close to sensitive electronic equipment, the electromagnetic field it generates will be directly coupled to these devices, affecting the performance of the equipment, and will interfere with the communication link of the fault warning system, resulting in signal distortion and increased bit error rate. By increasing the operating data fusion threshold of different collection points, unreliable data that may be affected by electromagnetic interference can be screened out to a certain extent, thereby improving the accuracy and reliability of data fusion and reducing the risk of erroneous fusion caused by interference.

[0017] Furthermore, the system of the present invention adjusts the rate of change of adjacent collection points by presetting a first false alarm rate and a second wave false alarm rate. Since equipment vibration may cause some components to undergo slight displacements, causing changes in parameters such as originally normal connections and gaps, the sensors monitoring these parameters will detect the numerical changes. The system cannot accurately distinguish whether it is normal component wear or temporary displacement caused by vibration, and may mistakenly judge it as a component failure and issue an early warning. By increasing the rate of change of adjacent collection points, high-rate-of-change signals in a short period of time can be ignored, and only alarms will be issued for displacements that have exceeded the limit for a long time, thereby avoiding misjudgment and improving the accuracy of fault warnings.

[0018] Furthermore, the system of the present invention adjusts the training enhancement ratio of missing data in the neural network model by presetting a first missing rate and a second missing rate. Since the data of some monitoring points in the data set are not uploaded in time or the data of certain time periods are blank due to equipment failure, the analysis results will be biased and unable to fully and accurately reflect the actual situation, affecting the model training and result accuracy. It may not be able to accurately describe the rules behind the data, resulting in inaccurate warning results. By increasing the training enhancement ratio of missing data in the neural network model, the model can have more opportunities to learn samples containing missing data, thereby better adapting to the situation of missing data, improving the model's processing ability for missing data, reducing the deviation caused by missing data, and further improving the accuracy of fault warning.

[0019] Furthermore, the system of the present invention adjusts the operating data fusion threshold of different collection points by presetting the signal-to-noise ratio. Since there may be various electromagnetic interference sources around the cage ship, such as the generator on the ship is installed too close to sensitive electronic equipment, the electromagnetic field it generates will be directly coupled to these devices, affecting the performance of the equipment, and will interfere with the communication link of the fault warning system, resulting in signal distortion and increased bit error rate. By increasing the operating data fusion threshold of different collection points, unreliable data that may be affected by electromagnetic interference can be screened out to a certain extent, thereby improving the accuracy and reliability of data fusion, reducing the risk of erroneous fusion due to interference, and further improving the accuracy of fault warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a block diagram of the overall structure of the cage vessel fault warning system according to an embodiment of the present invention; Figure 2 This is a logic flow chart of a process for determining the rate of change of adjacent collection points in a cage vessel fault warning system according to an embodiment of the present invention; Figure 3 This is a logic flow chart of a process for determining a training enhancement ratio of missing data in a neural network model of a cage vessel fault early warning system according to an embodiment of the present invention; Figure 4This is a logic flow chart of a process for determining the fusion threshold value of operating data at different collection points in a cage vessel fault warning system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0022] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0023] See also Figure 1 、 Figure 2 、 Figure 3 as well as Figure 4 As shown in the figure, they are respectively a block diagram of the overall structure of the cage vessel fault warning system according to an embodiment of the present invention, a logic flow chart of the process of determining the rate of change of adjacent acquisition points, a logic flow chart of the process of determining the training enhancement ratio of missing data in the neural network model, and a logic flow chart of the process of determining the running data fusion threshold of different acquisition points. A cage vessel fault warning system according to the present invention includes: The data acquisition module includes a collection unit for collecting operating data of each collection point of the cage vessel and a data transmission unit connected to the collection unit for converting the operating data into a communication signal and transmitting the signal to the monitoring center; a data processing module connected to the data acquisition module, comprising a preprocessing unit for preprocessing the communication signal to output normalized data, and a data analysis unit connected to the preprocessing unit for performing early warning analysis on the normalized data using a neural network model to output analysis results; an early warning module, connected to the data processing module, for issuing a fault early warning based on the analysis result; A control module is respectively connected to the data acquisition module, the data processing module and the early warning module, and is used to determine the change rate of adjacent acquisition points based on the false alarm rate of the fault early warning, or to determine the training enhancement ratio of missing data in the neural network model based on the byte missing rate of the normalized data, and to determine the operating data fusion threshold of different acquisition points based on the signal-to-noise ratio of the communication signal.

[0024] Specifically, the operating data includes the engine speed, the inverter temperature, and the tilt angle of the hull.

[0025] Specifically, preprocessing includes converting signals into data, removing noise, handling missing values, and normalization.

[0026] Specifically, neural network models include feedforward neural networks, convolutional neural networks, and recurrent neural networks.

[0027] Specifically, the normalized data includes the engine speed after noise removal, the temperature of the inverter after processing missing values, and the inclination angle of the hull after normalization.

[0028] Specifically, the analysis results include alarm time, alarm type, and fault frequency.

[0029] Specifically, the false alarm rate of fault warning is the ratio of the number of times warning signals are issued incorrectly to the total number of times warning signals are issued.

[0030] Specifically, the erroneous issuance of warning signals is due to sensor failure, signal transmission error, data processing algorithm error or interference from environmental factors, which causes the warning system to misjudge normal equipment operating parameters as abnormal, thereby issuing a warning signal.

[0031] Specifically, the rate of change of adjacent collection points is the ratio of the difference between the measurement values ​​of two collection points adjacent in time (the value at the latter moment minus the value at the previous moment) to the measurement value of the previous collection point.

[0032] Specifically, the byte missing rate of normalized data is the ratio of the number of missing bytes in the normalized data to the total number of bytes in the normalized data.

[0033] Specifically, the training enhancement ratio of missing data in the neural network model is the ratio of the number of data with missing values ​​added during the training process of the neural network model to the number of original data with missing values.

[0034] Specifically, the signal-to-noise ratio of a communication signal is the ratio of the communication signal power to the additive white Gaussian noise power.

[0035] Specifically, the fusion threshold of the running data from different collection points is a boundary value used to determine whether to fuse the data from different collection points.

[0036] During implementation, the system of the present invention adjusts the change rate of adjacent collection points according to the false alarm rate of fault warning by setting up a data acquisition module, a data processing module, an early warning module and a control module. Since equipment vibration may cause some components to undergo slight displacement, causing changes in parameters such as originally normal connections and gaps, the sensors monitoring these parameters will detect the numerical changes. The system cannot accurately distinguish whether it is normal component wear or temporary displacement caused by vibration, and may mistakenly judge it as a component failure and issue an early warning. By increasing the change rate of adjacent collection points, high change rate signals in a short period of time can be ignored, and only alarms are given for displacements that are stable and exceed the limit for a long time, thereby avoiding misjudgment. The training enhancement ratio of missing data in the neural network model is adjusted according to the byte loss rate of normalized data. Since the data of some monitoring points in the data set are not uploaded in time or the data of certain periods are blank due to equipment failure, the analysis results will be biased and unable to fully and accurately reflect the actual situation, affecting model training and conclusion. If the accuracy of the result is low, it may not be able to accurately describe the rules behind the data, resulting in inaccurate warning results. By increasing the training enhancement ratio of missing data in the neural network model, the model can have more opportunities to learn samples containing missing data, so as to better adapt to the situation of missing data, improve the model's ability to process missing data, and reduce the deviation caused by missing data. The operating data fusion threshold of different collection points is adjusted according to the signal-to-noise ratio of the communication signal. Since there may be various electromagnetic interference sources around the cage ship, such as the generator on the ship is installed too close to sensitive electronic equipment, the electromagnetic field it generates will be directly coupled to these devices, affecting the performance of the equipment, and will interfere with the communication link of the fault warning system, resulting in signal distortion and increased bit error rate. By increasing the operating data fusion threshold of different collection points, unreliable data that may be affected by electromagnetic interference can be screened out to a certain extent, thereby improving the accuracy and reliability of data fusion and reducing the risk of incorrect fusion due to interference.

[0037] Specifically, the control module is used to determine whether the accuracy of the fault warning meets the requirements based on the false alarm rate of the fault warning. If the false alarm rate of the fault warning is greater than the preset first false alarm rate, it is determined that the accuracy of the fault warning does not meet the requirements.

[0038] Specifically, the control module is used to preliminarily determine that the effectiveness of the warning analysis does not meet the requirements when the false alarm rate of the fault warning is greater than the preset first false alarm rate and less than or equal to the preset second false alarm rate, and to determine whether the effectiveness of the warning analysis meets the requirements based on the byte missing rate of the normalized data.

[0039] It can be understood that the three intervals divided by the preset first false alarm rate and the preset second false alarm rate correspond to three situations respectively: The first interval is when the false alarm rate of the fault warning is less than or equal to the preset first false alarm rate, corresponding to the situation that: it is determined that the accuracy of the fault warning meets the requirements; The second interval is when the false alarm rate of the fault warning is greater than the preset first false alarm rate and less than or equal to the preset second false alarm rate. This corresponds to the following situations: due to the fact that data from some monitoring points in the dataset were not uploaded in time or equipment failures resulted in blank data for certain periods of time, the analysis results will be biased and unable to fully and accurately reflect the actual situation, affecting model training and result accuracy. It may not be possible to accurately describe the patterns behind the data, resulting in inaccurate warning results. The third interval is when the false alarm rate of the fault warning is greater than the preset second false alarm rate. The corresponding situation is: due to equipment vibration, some components may undergo slight displacement, causing changes in parameters such as normal connections and gaps. The sensors monitoring these parameters will detect the numerical changes. The system cannot accurately distinguish whether it is normal component wear or temporary displacement caused by vibration, and may mistakenly judge it as a component failure and issue a warning.

[0040] It is understood that the preset false alarm rate can be set based on historical data to ensure the accuracy and practicality of test results. Alternatively, the preset false alarm rate is determined by analyzing past operational data of the cage vessel fault warning system, calculating the ratio of actual false alarms to total alarms over a specific period, and using this as a reference to determine the range of values. For example, the preset first false alarm rate is typically set within the range of [1% to 3%], and the preset second false alarm rate is typically set within the range of [4% to 6%].

[0041] Preferably, the first false alarm rate is preset to be 2%, and the second false alarm rate is preset to be 5%.

[0042] Specifically, the control module is used to increase the change rate of adjacent collection points when the false alarm rate of the fault warning is greater than the preset second false alarm rate; The increase range of the change rate of adjacent collection points is determined by the difference between the false alarm rate of the fault warning and a preset second false alarm rate.

[0043] Specifically, when the difference between the false alarm rate of the fault warning and the preset second false alarm rate is within 1%, the change rate of adjacent collection points increases to 1.2 times the original value; when the difference between the false alarm rate of the fault warning and the preset second false alarm rate exceeds 1%, on the basis of the increase to 1.2 times the original value, the change rate of adjacent collection points increases by 1% for every 0.5% that exceeds it. For example, if the difference between the false alarm rate of the fault warning and the preset second false alarm rate is 2%, the current change rate of adjacent collection points is 5%, and the increased change rate of adjacent collection points is 5×1.2+1×2=8%.

[0044] Specifically, the rate of change of adjacent collection points in this scheme is the rate of change of the tank pressure in the cage ship.

[0045] During implementation, the system of the present invention adjusts the rate of change of adjacent collection points by presetting a first false alarm rate and a second wave false alarm rate. Since equipment vibration may cause some components to undergo slight displacements, causing changes in originally normal connection, gap and other parameters, the sensors monitoring these parameters will detect the numerical changes. The system cannot accurately distinguish whether it is normal component wear or temporary displacement caused by vibration, and may mistakenly judge it as a component failure and issue an early warning. By increasing the rate of change of adjacent collection points, high change rate signals in a short period of time can be ignored, and only alarms will be issued for displacements that have exceeded the limit for a long time, thereby avoiding misjudgment and improving the accuracy of fault warnings.

[0046] Specifically, the control module is used to determine whether the effectiveness of the warning analysis meets the requirements based on the byte missing rate of the normalized data. If the byte missing rate of the normalized data is greater than the preset first missing rate, it is determined that the effectiveness of the warning analysis does not meet the requirements.

[0047] Specifically, the control module is used to increase the training enhancement ratio of missing data in the neural network model when the byte missing rate of the normalized data is greater than the preset first missing rate and less than or equal to the preset second missing rate.

[0048] Specifically, the control module is used to preliminarily determine that the transmission stability of the operating data does not meet the requirements when the byte loss rate of the normalized data is greater than the preset second loss rate, and determine whether the transmission stability of the operating data meets the requirements based on the signal-to-noise ratio of the communication signal.

[0049] It can be understood that the three intervals divided by the preset first missing rate and the preset second missing rate correspond to three situations respectively: The first interval is when the byte missing rate of the normalized data is less than or equal to the preset first missing rate, corresponding to the situation that: the effectiveness of the early warning analysis is determined to meet the requirements; The second interval is when the byte loss rate of the normalized data is greater than the preset first loss rate and less than or equal to the preset second loss rate. This corresponds to the following situations: due to the fact that data from some monitoring points in the dataset were not uploaded in a timely manner or equipment failures resulted in data gaps in certain periods, the analysis results will be biased and unable to fully and accurately reflect the actual situation, affecting model training and result accuracy. It may also be impossible to accurately describe the patterns behind the data, resulting in inaccurate warning results. The third interval is when the byte loss rate of the normalized data is greater than the preset second loss rate. The corresponding situation is: since there may be various electromagnetic interference sources around the cage ship, such as the generator on the ship is installed too close to sensitive electronic equipment, the electromagnetic field it generates will directly couple to these devices, affecting the performance of the equipment, and will interfere with the communication link of the fault warning system, resulting in signal distortion and increased bit error rate.

[0050] It is understood that the preset data loss rate can be set based on a system performance evaluation, intended to ensure the accuracy and practicality of test results. Optionally, the preset data loss rate is determined by evaluating system performance to determine a tolerable data loss rate range, taking into account the overall performance requirements of the cage vessel fault warning system, including data acquisition, transmission, storage, and processing, to ensure the system's normal operation and provide accurate warning information. For example, the preset first data loss rate is generally selected from the range of [0.3%, 0.5%], and the preset second data loss rate is generally selected from the range of [0.6%, 0.8%].

[0051] Preferably, the preferred embodiment of the preset first missing rate is 0.4%, and the preferred embodiment of the preset second missing rate is 0.7%.

[0052] Specifically, the increase in the training enhancement ratio of missing data in the neural network model is determined by the difference between the byte missing rate of the normalized data and a preset first missing rate.

[0053] Specifically, when the difference between the byte missing rate of the normalized data and the preset first missing rate is within 0.2%, the training enhancement ratio of missing data in the neural network model is increased to 1.2 times the original value. When the difference between the byte missing rate of the normalized data and the preset first missing rate exceeds 0.2%, on the basis of the increase to 1.2 times the original value, the training enhancement ratio of missing data in the neural network model is increased by 2% for every 0.1% that exceeds it. For example, the difference between the byte missing rate of the normalized data and the preset first missing rate is 0.4%, the current training enhancement ratio of missing data in the neural network model is 15%, and the increased training enhancement ratio of missing data in the neural network model is 15×1.2+2×2=22%.

[0054] During implementation, the system of the present invention adjusts the training enhancement ratio of missing data in the neural network model by setting a preset first missing rate and a preset second missing rate. Since the data of some monitoring points in the data set are not uploaded in time or the data of certain time periods are blank due to equipment failure, the analysis results will be biased and unable to fully and accurately reflect the actual situation, affecting the model training and result accuracy. It may not be able to accurately describe the laws behind the data, resulting in inaccurate warning results. By increasing the training enhancement ratio of missing data in the neural network model, the model can have more opportunities to learn samples containing missing data, thereby better adapting to the situation of missing data, improving the model's ability to process missing data, reducing the deviation caused by missing data, and further improving the accuracy of fault warnings.

[0055] Specifically, the control module is used to determine whether the transmission stability of the operating data meets the requirements based on the signal-to-noise ratio of the communication signal. If the signal-to-noise ratio of the communication signal is less than the preset signal-to-noise ratio, it is determined that the transmission stability of the operating data does not meet the requirements, and the operating data fusion threshold of different collection points is increased.

[0056] It is understandable that the two intervals divided by the preset signal-to-noise ratio correspond to two situations: The first interval is when the signal-to-noise ratio of the communication signal is less than the preset signal-to-noise ratio. This corresponds to the following situation: there may be various electromagnetic interference sources around the cage ship. For example, the generator on the ship is installed too close to sensitive electronic equipment. The electromagnetic field generated by the generator will directly couple to these devices, affecting the performance of these devices and interfering with the communication link of the fault warning system, resulting in signal distortion and increased bit error rate. The second interval is when the signal-to-noise ratio of the communication signal is greater than or equal to the preset signal-to-noise ratio, and the corresponding situation is: determining that the transmission stability of the operating data meets the requirements.

[0057] It is understood that the preset signal-to-noise ratio can be set based on sensor performance parameters. The preset signal-to-noise ratio is intended to ensure the accuracy and practicality of test results. Optionally, the preset signal-to-noise ratio is determined by collecting historical operational data from the cage vessel fault warning system, including sensor data and system logs, and analyzing the frequency and distribution of missing values ​​in this data to understand the patterns of missing values ​​in different data types. For example, the preset signal-to-noise ratio is typically selected within the range of [20dB, 25dB].

[0058] Preferably, the preset signal-to-noise ratio is 23 dB.

[0059] Specifically, the increase range of the operation data fusion threshold of different collection points is determined by the difference between the signal-to-noise ratio of the communication signal and the preset signal-to-noise ratio.

[0060] Specifically, when the difference between the signal-to-noise ratio of the communication signal and the preset signal-to-noise ratio is within 2dB, the operating data fusion threshold of different collection points is increased to 1.5 times the original value; when the difference between the signal-to-noise ratio of the communication signal and the preset signal-to-noise ratio exceeds 2dB, on the basis of the increase to 1.5 times the original value, the operating data fusion threshold of different collection points is increased by 0.1 for every 1dB exceeding. For example, when the difference between the signal-to-noise ratio of the communication signal and the preset signal-to-noise ratio is 3dB, the current operating data fusion threshold of different collection points is 0.4, and the increased operating data fusion threshold of different collection points is 0.4×1.5+1×0.1=0.7.

[0061] During implementation, the system of the present invention adjusts the operating data fusion threshold of different collection points by presetting the signal-to-noise ratio. Since there may be various electromagnetic interference sources around the cage ship, such as the generator on the ship is installed too close to sensitive electronic equipment, the electromagnetic field it generates will be directly coupled to these devices, affecting the performance of the equipment, and will interfere with the communication link of the fault warning system, resulting in signal distortion and increased bit error rate. By increasing the operating data fusion threshold of different collection points, unreliable data that may be affected by electromagnetic interference can be screened out to a certain extent, thereby improving the accuracy and reliability of data fusion, reducing the risk of erroneous fusion due to interference, and further improving the accuracy of fault warning.

[0062] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A cage vessel fault warning system, characterized in that: include: The data acquisition module includes a collection unit for collecting operating data of each collection point of the cage vessel and a data transmission unit connected to the collection unit for converting the operating data into a communication signal and transmitting the signal to the monitoring center; a data processing module connected to the data acquisition module, comprising a preprocessing unit for preprocessing the communication signal to output normalized data and a data analysis unit connected to the preprocessing unit for performing early warning analysis on the normalized data using a neural network model to output analysis results; an early warning module, connected to the data processing module, for issuing a fault early warning based on the analysis result; A control module is respectively connected to the data acquisition module, the data processing module and the early warning module, and is used to determine the change rate of adjacent acquisition points based on the false alarm rate of the fault early warning, or to determine the training enhancement ratio of missing data in the neural network model based on the byte missing rate of the normalized data, and to determine the operating data fusion threshold of different acquisition points based on the signal-to-noise ratio of the communication signal.

2. The cage vessel fault warning system according to claim 1, characterized in that: The control module is used to determine whether the accuracy of the fault warning meets the requirements based on the false alarm rate of the fault warning. If the false alarm rate of the fault warning is greater than a preset first false alarm rate, it is determined that the accuracy of the fault warning does not meet the requirements.

3. The cage vessel fault warning system according to claim 2, characterized in that: The control module is used to preliminarily determine that the effectiveness of the warning analysis does not meet the requirements when the false alarm rate of the fault warning is greater than the preset first false alarm rate and less than or equal to the preset second false alarm rate, and to determine whether the effectiveness of the warning analysis meets the requirements based on the byte missing rate of the normalized data.

4. The cage vessel fault warning system according to claim 3, characterized in that: The control module is configured to increase the rate of change of adjacent collection points when the false alarm rate of the fault warning is greater than the preset second false alarm rate; The increase range of the change rate of adjacent collection points is determined by the difference between the false alarm rate of the fault warning and a preset second false alarm rate.

5. The cage vessel fault warning system according to claim 4, characterized in that: The control module is used to determine whether the effectiveness of the early warning analysis meets the requirements based on the byte missing rate of the normalized data. If the byte missing rate of the normalized data is greater than a preset first missing rate, it is determined that the effectiveness of the early warning analysis does not meet the requirements.

6. The cage vessel fault warning system according to claim 5, characterized in that: The control module is used to increase the training enhancement ratio of missing data in the neural network model when the byte missing rate of the normalized data is greater than the preset first missing rate and less than or equal to the preset second missing rate.

7. The cage vessel fault warning system according to claim 6, characterized in that: The control module is used to preliminarily determine that the transmission stability of the operating data does not meet the requirements when the byte loss rate of the normalized data is greater than the preset second loss rate, and determine whether the transmission stability of the operating data meets the requirements based on the signal-to-noise ratio of the communication signal.

8. The cage vessel fault warning system according to claim 7, characterized in that: The increase in the training enhancement ratio of missing data in the neural network model is determined by the difference between the byte missing rate of the normalized data and a preset first missing rate.

9. The cage vessel fault warning system according to claim 8, characterized in that: The control module is used to determine whether the transmission stability of the operating data meets the requirements based on the signal-to-noise ratio of the communication signal. If the signal-to-noise ratio of the communication signal is less than a preset signal-to-noise ratio, it is determined that the transmission stability of the operating data does not meet the requirements, and the operating data fusion threshold of different collection points is increased.

10. The cage vessel fault warning system according to claim 9, characterized in that: The increase range of the operation data fusion threshold of different collection points is determined by the difference between the preset signal-to-noise ratio and the signal-to-noise ratio of the communication signal.

Images