Offshore wind power cable monitoring and early warning system and method based on digital twinning

Abstract

The application discloses an offshore wind power cable monitoring and early warning system and method based on digital twinning, relates to the technical field of digital twinning and industrial internet of things monitoring, and comprises the following modules: a data acquisition module, which is used for acquiring real-time multidimensional sensing data of a submarine cable and determining real-time heat generation power of the cable; a physical law model module, which is used for outputting a theoretical prediction state; a data-driven model module, which is used for outputing a data fitting state; a bidirectional dynamic coupling module, which is used for generating a mismatch discrimination result indicating cognitive mismatch or cognitive consistency; a model correction module, which is used for outputting a corrected theoretical prediction state; a state evaluation and early warning module, which is used for generating a comprehensive evaluation result; and a comparison between the comprehensive evaluation result and a preset multi-level risk threshold according to a change trend of the comprehensive evaluation result, and early warning information is issued. The application can break through the limitation of a traditional physical model and correct itself when encountering extreme unknown working conditions, and effectively inspects and prevents deep risks.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital twinning and industrial internet of things monitoring, more specifically, the present application relates to a marine wind power cable monitoring and early warning system and method based on digital twinning. BACKGROUND

[0002] The submarine cable of the offshore wind power facility faces severe challenges in safe and stable operation due to long-term exposure to complex and variable marine environments. The existing technology uses digital twinning for monitoring, which is usually based on first principles to construct physical law models. The fatal flaw of such models is that their internal laws and assumptions are static and unchangeable once established. When encountering complex extreme marine events such as typhoons and submarine landslides, the actual physical boundary conditions of the cable, such as seabed coverage and surrounding medium thermal conductivity, will change dramatically, exceeding the original assumptions of the physical model. At this time, the physical model itself cannot reflect the physical reality, resulting in the loss of early warning capability of the entire twinning system for unknown risks.

[0003] Therefore, how to construct a new monitoring and early warning paradigm that can dynamically adapt to environmental changes and has self-correcting ability is a technical problem that needs to be solved in the field.

[0004] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a marine wind power cable monitoring and early warning system and method based on digital twinning, the technical scheme is as follows, a marine wind power cable monitoring and early warning system based on digital twinning, comprising:

[0006] A data acquisition module is configured to acquire real-time multi-dimensional sensing data of the submarine cable, wherein the real-time multi-dimensional sensing data includes real-time working condition data, and the real-time heat generation power of the cable is determined according to the real-time working condition data.

[0007] A physical law model module is configured to receive the real-time multi-dimensional sensing data and output a theoretical prediction state.

[0008] A data-driven model module is configured to receive the real-time multi-dimensional sensing data in parallel and output a data fitting state.

[0009] A bidirectional dynamic coupling module is configured to acquire the theoretical prediction state and the data fitting state, calculate a model cognitive bias, compare the model cognitive bias with a preset cognitive mismatch threshold, and generate a mismatch discrimination result indicating cognitive mismatch or cognitive consistency.

[0010] a model correction module, configured to, in response to the mismatch determination result being cognitive mismatch, calculate a physical parameter correction amount based on a preset adaptive gain, update the physical law model module by using the physical parameter correction amount, and output a corrected theoretical prediction state;

[0011] a state assessment and early warning module, configured to, when the mismatch determination result is cognitive consistency, fuse the theoretical prediction state and the data fitting state to generate a comprehensive assessment result; when the mismatch determination result is cognitive mismatch, fuse the corrected theoretical prediction state output by the model correction module and the data fitting state to generate the comprehensive assessment result; and compare the comprehensive assessment result and a change trend of the comprehensive assessment result with a plurality of preset risk threshold values to issue early warning information.

[0012] Optionally, the physical law model is a long short-term memory network model based on a finite element method.

[0013] Optionally, the model cognitive bias is calculated by normalizing a difference between the theoretical prediction state and the data fitting state by an absolute value of the data fitting state.

[0014] Optionally, the cognitive mismatch threshold is determined by statistically analyzing model cognitive biases generated under historical normal working conditions and taking a percentile point of a distribution of the model cognitive biases.

[0015] Optionally, the model correction module calculates the physical parameter correction amount by normalizing a difference between the theoretical prediction state and the data fitting state by the real-time heat generation power of the cable and multiplying the preset adaptive gain.

[0016] Optionally, the real-time working condition data include real-time current obtained from a power grid SCADA system, and the real-time heat generation power of the cable is determined according to the real-time current and a known resistance of the cable.

[0017] Optionally, the plurality of risk threshold values include attention, warning, and danger levels.

[0018] A digital-twin-based offshore wind power cable monitoring and early warning method, comprising:

[0019] obtaining real-time multi-dimensional sensing data of a submarine cable, the real-time multi-dimensional sensing data including real-time working condition data, and determining a real-time heat generation power of the cable according to the real-time working condition data;

[0020] parallel processing the real-time multi-dimensional sensing data to obtain a theoretical prediction state and a data fitting state, respectively;

[0021] a model cognitive bias between the theoretical prediction state and the data fitting state is calculated, the model cognitive bias is compared with a preset cognitive mismatch threshold, and a mismatch discrimination result indicating cognitive mismatch or cognitive consistency is generated;

[0022] If the mismatch discrimination result is cognitive mismatch, a physical parameter correction amount based on a preset adaptive gain is calculated, the physical law model is updated to obtain a corrected theoretical prediction state, and the next step is entered.

[0023] If the mismatch discrimination result is cognitive consistency, the theoretical prediction state and the data fitting state are fused to generate a comprehensive evaluation result.

[0024] According to the comprehensive evaluation result and the change trend of the comprehensive evaluation result, a multi-level risk threshold is compared, and warning information is issued.

[0025] Compared with the prior art, the present application has the following beneficial effects:

[0026] 1. The present application can break through the limitations of traditional physical models, and can self-correct in extreme unknown working conditions such as typhoons and submarine landslides, rather than system failure, thereby realizing effective insight and prevention of deep-seated risks.

[0027] 2. The present application can scientifically distinguish between normal prediction fluctuations and abnormal deviations caused by real environmental changes by statistically analyzing the model cognitive bias under historical normal working conditions, greatly improving the reliability of the system in complex marine environments.

[0028] 3. When the physical model deviates from the real data, the system actively intervenes, and according to the real situation revealed by the data-driven model, the key parameters in the physical law model are corrected in reverse, forming a closed loop feedback, forcing the physical model to evolve in a direction that is more consistent with the physical reality.

[0029] 4. By setting multi-level risk thresholds such as attention, warning and danger, the cable health state is finely evaluated and graded, making the warning information more forward-looking and operable, and helping operation and maintenance personnel to make more reasonable and effective resource allocation and decision response, realizing the change from passive response to active prevention. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 The system flowchart of the present application.

[0031] Figure 2A method flowchart of the present application. DETAILED DESCRIPTION

[0032] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present application.

[0033] Embodiment 1

[0034] Please refer to Figure 1 A digital-twin-based offshore wind power cable monitoring and early warning system comprises:

[0035] A data acquisition module is configured to acquire real-time multi-dimensional sensing data of a submarine cable, wherein the real-time multi-dimensional sensing data comprises real-time working condition data, and the real-time working condition data is used to determine real-time heat generation power of the cable.

[0036] A physical law model module is configured to receive the real-time multi-dimensional sensing data and output a theoretical prediction state.

[0037] A data-driven model module is configured to receive the real-time multi-dimensional sensing data in parallel and output a data fitting state.

[0038] A bidirectional dynamic coupling module is configured to acquire the theoretical prediction state and the data fitting state, calculate a model cognitive bias, compare the model cognitive bias with a preset cognitive mismatch threshold, and generate a mismatch discrimination result indicating cognitive mismatch or cognitive consistency.

[0039] A model correction module is configured to, in response to the mismatch discrimination result being cognitive mismatch, calculate a physical parameter correction amount based on a preset adaptive gain, update the physical law model module by using the physical parameter correction amount, and output a corrected theoretical prediction state.

[0040] A state assessment and early warning module is configured to, when the mismatch discrimination result is cognitive consistency, fuse the theoretical prediction state and the data fitting state to generate a comprehensive assessment result; when the mismatch discrimination result is cognitive mismatch, fuse the corrected theoretical prediction state output by the model correction module and the data fitting state to generate a comprehensive assessment result; and compare the comprehensive assessment result and a change trend of the comprehensive assessment result with a preset multi-level risk threshold to issue early warning information.

[0041] The digital-twin-based offshore wind power cable monitoring and early warning system provided by the present application breaks through the limitations of existing physical models, which are fixed and cannot adapt to dramatic changes in marine environments.

[0042] The system continuously captures the actual operation data of the submarine cable by a data acquisition module, for example, by using distributed optical fiber sensing technology; the data are simultaneously transmitted to the physical law model module and the data-driven model module, forming a double-path parallel prediction architecture; the technical key of the parallel prediction architecture is to quantitatively determine the cognitive bias between the two models in real time by using a bidirectional dynamic coupling module, and once the bias exceeds the normal fluctuation range in a statistical sense, it is determined that the physical model has been distorted; at this time, the model correction module is not limited to passive warning, but actively intervenes, and according to the real situation revealed by the data-driven model, the key parameters in the physical law model are reconstructed in reverse; finally, the state evaluation and early warning module fuses the optimal model output after dynamic verification or correction, evaluates the health state of the cable and issues multi-level early warning;

[0043] Such an architecture enables the system to self-correct rather than systematically fail when encountering extreme unknown working conditions such as typhoons and submarine landslides, thereby achieving effective insight and prevention of deep-seated risks.

[0044] Embodiment 2

[0045] The physical law model is a long short-term memory network model based on the finite element method;

[0046] The calculation method of the model cognitive bias is to normalize the difference between the theoretical prediction state and the data fitting state by the absolute value of the data fitting state;

[0047] To further illustrate, in the specific implementation of the present application, the physical law model module is a thermal-mechanical coupling model based on the finite element method, which is established according to prior knowledge such as the design blueprint of the cable and the marine geological survey report, to describe its theoretical thermodynamic behavior; in parallel, the data-driven model module uses a long short-term memory network to capture complex nonlinear correlations by learning from massive historical operation data; the core function of the bidirectional dynamic coupling module is realized by a specific quantitative formula, which aims to generate the model cognitive bias; the internal logic is that in order to objectively measure the deviation between the physical model and the real data, the influence of the physical dimension and the numerical amplitude must be eliminated, so a dimensionless index is constructed by referring to the idea of the standardized relative error in statistics; in the scenario of cognitive mismatch, the data-driven model is regarded as a reference system that is closer to the physical reality, so its output is normalized;

[0048] The calculation formula of the model cognitive bias is:

[0049] ;

[0050] wherein, is the model cognitive bias at the moment t, ​The theoretical predicted states output by the physical law model module, such as predicted temperature. The data fitting state output by the data-driven model module corresponds to the same physical quantity. It is a positive real constant, set up to prevent the denominator from being zero, whose value is much smaller than the normal measured value, and whose dimensions are the same as... The same; the bidirectional dynamic coupling module uses this formula for continuous calculation. This calculation result is the key criterion for triggering adaptive correction of the model;

[0051] By comparing a dynamically changing, standardized deviation value with a fixed threshold, the system can accurately identify the moment of failure of the physical model, thereby initiating the subsequent correction process and ensuring the entire twin system's ability to perceive unknown risks.

[0052] Example 3

[0053] The cognitive mismatch threshold is determined by statistically analyzing the cognitive biases of the model generated under historical normal working conditions and taking the percentile of its distribution.

[0054] The logic for setting the cognitive mismatch threshold abandons the human-based setting method that relies on experience, and its working principle is driven by statistical principles. The system must be able to distinguish between normal prediction fluctuations of the model and abnormal deviations caused by real changes in the physical environment. A scientific threshold should maximize the sensitivity to real anomalies while minimizing the false alarm rate caused by data noise.

[0055] Specifically, the threshold is determined by the system first collecting and storing a large number of historical cognitive biases under normal operating conditions. This results in a large statistical dataset; subsequently, probability distribution analysis is performed on this dataset, and a high percentile of this distribution, such as the 99th percentile, is selected as the cognitive mismatch threshold. Based on this method, the system establishes a dynamic boundary for normal behavior; any deviation exceeding this boundary, i.e. All of these will be judged with high confidence as a cognitive mismatch event, thereby reliably triggering the model correction module;

[0056] This mechanism greatly improves the reliability of the system in complex marine environments and avoids frequent false triggers or missed detections of critical risks due to improper threshold settings.

[0057] Example 4

[0058] The model correction module calculates the physical parameter correction amount in the following way: the difference between the theoretical prediction state and the data fitting state is normalized by the real-time heat generation power of the cable and multiplied by the preset adaptive gain.

[0059] Real-time operating data includes real-time current obtained from the power grid SCADA system. The real-time heat generation power of the cable is determined by calculation based on the real-time current and the known resistance of the cable.

[0060] When a cognitive mismatch is confirmed, the model correction module is immediately activated. Its core task is to calculate the correction amount for physical parameters, which is a crucial step in achieving cognitive resilience of the system. The formula for calculating this correction amount is derived from the fundamental relationship of steady-state thermodynamics. It reveals the relationship between temperature difference deviation and real-time heat generation power of the cable. Strong correlation; in order to maintain consistency and stability of the correction process under different load conditions, the temperature difference must be normalized using real-time heat generation power;

[0061] The formula for calculating the correction amount of this physical parameter is:

[0062]

[0063] in, for The physical parameter correction calculated at any time, taking equivalent thermal resistance as an example here; It is a dimensionless adaptive gain hyperparameter; This represents the difference between the fitted data state and the theoretically predicted state. The real-time heat generation power of the cable is obtained by acquiring the real-time current from the power grid SCADA system. and known resistance per unit length of cable According to Joule's law Calculated; This is a minimum normal power value representing non-Joule heating effects such as dielectric loss, set to avoid computational divergence near zero load; adaptive gain. The determination method is to calibrate through offline simulation experiments, simulating a known physical parameter mutation event in the simulation environment, and then debugging... The value of the correction process is to find an optimal value within the range of 0.01 to 1.0 that allows the correction process to converge the fastest without oscillation.

[0064] Based on the above results, the model correction module calculated... Then, it is immediately used to update the corresponding parameters in the physical law model, for example. ,in, For old parameters, For the updated parameters;

[0065] This process forms a tight closed-loop feedback loop, forcing the physical model to evolve online and in real time toward a direction that is more in line with physical reality.

[0066] Example 5

[0067] The multi-level risk threshold includes attention, alarm and danger levels;

[0068] The state assessment and early warning module is the final output end of the system, and the multi-level risk threshold it relies on is a pre-set rule system.

[0069] For high-value assets such as offshore wind power, a single binary safety judgment is too rough and cannot meet the needs of fine operation and risk management. Providing graded early warnings can help operation personnel make more reasonable and effective resource allocation and decision response; the pre-set multi-level risk threshold is defined as three levels: attention, alarm and danger; these thresholds are for the comprehensive assessment results of the system And set; the comprehensive assessment results are generated by fusing the theoretical prediction state and the data fitting state, and after cognitive mismatch occurs, the theoretical prediction state and the data fitting state are fused after correction; the application effect of the multi-level risk threshold is that the system can compare the current value and its trend over time with the three thresholds, and thus issue early warning information of different levels;

[0070] Attention level: the lowest level of early warning; triggered when the value of the comprehensive assessment results or its trend first reaches the pre-set attention threshold, which indicates that the health state of the cable has a slight but noticeable deviation, although it does not constitute a direct threat, but the system will mark it and prompt the operation personnel to need to continuously observe and track the data of the cable section;

[0071] Alarm level: medium level of early warning; triggered when the value of the comprehensive assessment results further deteriorates, its value or trend exceeds the attention level and reaches the alarm threshold, which indicates that the health state of the cable has more significant abnormalities, and potential risks have been formed. The alarm information issued by the system aims to prompt the operation personnel to include this problem in the work plan and prepare for more detailed analysis or arrange for a near-term inspection.

[0072] Danger level: the highest level of early warning; triggered when the value of the comprehensive assessment results or its trend reaches or exceeds the most serious danger threshold, which indicates that the cable may be on the edge of structural or functional damage, and the probability of failure significantly increases. The danger warning issued by the system is the highest priority instruction, requiring the operation personnel to immediately take intervention measures, such as adjusting the cable load or performing emergency shutdown maintenance, to avoid the occurrence of catastrophic failure.

[0073] ​The differentiated early warning mechanism makes the early warning information more forward-looking and operable, and realizes the transition from passive response to active prevention.

[0074] Embodiment 6

[0075] Please refer to Figure 2 A digital twin-based offshore wind power cable monitoring and early warning method, comprising:

[0076] Obtaining real-time multi-dimensional sensing data of the submarine cable, the real-time multi-dimensional sensing data comprising real-time working condition data, and determining real-time heat generation power of the cable according to the real-time working condition data;

[0077] Parallel processing of real-time multi-dimensional sensing data, respectively obtaining theoretical prediction state and data fitting state;

[0078] Calculating the model cognitive bias between the theoretical prediction state and the data fitting state, comparing the model cognitive bias with a preset cognitive mismatch threshold, and generating a mismatch discrimination result indicating cognitive mismatch or cognitive consistency;

[0079] Judging the mismatch discrimination result: if it is cognitive mismatch, calculating a physical parameter correction amount based on a preset adaptive gain, updating the physical law model to obtain a corrected theoretical prediction state, and entering the next step; if it is cognitive consistency, directly entering the next step;

[0080] State fusion: if the mismatch discrimination result is cognitive mismatch, fusing the corrected theoretical prediction state and the data fitting state; if the mismatch discrimination result is cognitive consistency, fusing the theoretical prediction state and the data fitting state to generate a comprehensive evaluation result;

[0081] According to the comprehensive evaluation result and the change trend of the comprehensive evaluation result, comparing with a preset multi-level risk threshold, and issuing an early warning information;

[0082] The monitoring and early warning method provided by the application strictly links the links of data sensing, double-mode comparison, dynamic correction and risk assessment; The initial step of the method is to continuously acquire real-time multi-dimensional sensing data of the submarine cable, and immediately calculate the real-time heat generation power of the cable according to the working condition data in the data; The collected data is sent into a double-track parallel processing process: the physical law model outputs the theoretical prediction state according to the physical law, and the data-driven model outputs the data fitting state based on the mode of historical data learning;

[0083] The key judgment mechanism of the flow is to calculate the model cognitive bias between the two states, compare it with the preset cognitive mismatch threshold, and determine whether the physical model is still valid; if it is determined that the cognitive mismatch, the method will seamlessly link to a closed-loop correction step: calculate the physical parameter correction and update the physical law model to obtain a more realistic corrected theoretical prediction state; After the judgment step, whether the cognition is consistent or not, the method will enter the state fusion step, combine the optimal theoretical prediction with the data fitting state to generate a comprehensive evaluation result; According to the comprehensive evaluation result and its trend, the method refers to the preset multi-level risk threshold to issue accurate early warning information and complete a complete monitoring and early warning cycle.

[0084] This method fundamentally improves the robustness and accuracy of the monitoring and early warning system by building a self-correcting closed loop that can dynamically adapt to environmental changes, ensuring the long-term safe and stable operation of offshore wind power facilities in complex and variable marine environments.

[0085] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited to this. Any skilled person in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A digital-twin-based offshore wind power cable monitoring and early warning system, characterized in that, The method comprises the following steps: a data acquisition module is configured to acquire real-time multi-dimensional sensing data of a submarine cable, wherein the real-time multi-dimensional sensing data comprises real-time operating condition data, and the real-time operating condition data is used to determine real-time heat generation power of the cable; a physical law model module is configured to receive the real-time multi-dimensional sensing data and output a theoretical prediction state, wherein the physical law model module is a thermal-mechanical coupling model constructed based on a finite element method; a data-driven model module is configured to receive the real-time multi-dimensional sensing data in parallel and output a data fitting state; a bidirectional dynamic coupling module is configured to acquire the theoretical prediction state and the data fitting state, calculate a model cognitive bias, compare the model cognitive bias with a preset cognitive mismatch threshold, and generate a mismatch discrimination result indicating cognitive mismatch or cognitive consistency, wherein the model cognitive bias is calculated by normalizing a difference between the theoretical prediction state and the data fitting state by an absolute value of the data fitting state; a calculation formula of the model cognitive bias is as follows: ； in, for Cognitive bias in models at any given moment The theoretically predicted state output by the physical law model module. The data fitting state output by the data-driven model module corresponds to the same physical quantity. It is a positive real constant, set up to prevent the denominator from being zero, whose value is much smaller than the normal measured value, and whose dimensions are the same as... The same; the bidirectional dynamic coupling module uses this formula for continuous calculation. ; a model correction module is configured to, in response to the mismatch discrimination result being cognitive mismatch, calculate a physical parameter correction amount based on a preset adaptive gain, update the physical law model module by using the physical parameter correction amount, and output a corrected theoretical prediction state; a state evaluation and early warning module is configured to, when the mismatch discrimination result is cognitive consistency, fuse the theoretical prediction state and the data fitting state to generate a comprehensive evaluation result; when the mismatch discrimination result is cognitive mismatch, fuse the corrected theoretical prediction state output by the model correction module and the data fitting state to generate the comprehensive evaluation result; compare the comprehensive evaluation result and a change trend of the comprehensive evaluation result with a plurality of preset risk threshold values, and issue a warning message, wherein the plurality of risk threshold values comprise attention, alarm and danger levels.

2. The system of claim 1, wherein, The cognitive mismatch threshold is determined by statistically analyzing model cognitive biases generated under historical normal operating conditions and taking a percentile point of a distribution of the model cognitive biases.

3. The system of claim 1, wherein, The model correction module calculates the physical parameter correction amount by normalizing a difference between the theoretical prediction state and the data fitting state by the real-time heat generation power of the cable and multiplying the difference by the preset adaptive gain.

4. The system of claim 3, wherein, The real-time operating condition data comprises real-time current acquired from a power grid SCADA system, and the real-time heat generation power of the cable is determined according to the real-time current and a known resistance of the cable.

5. A digital-twin-based offshore wind power cable monitoring and early warning method, characterized in that, The method comprises the following steps: acquiring real-time multi-dimensional sensing data of a submarine cable, wherein the real-time multi-dimensional sensing data comprises real-time operating condition data, and real-time heat generation power of the cable is determined according to the real-time operating condition data; receiving the real-time multi-dimensional sensing data by a thermal-mechanical coupling physical law model constructed based on a finite element method, outputting a theoretical prediction state, and simultaneously and in parallel processing the real-time multi-dimensional sensing data by a data-driven model to obtain a data fitting state; The model cognitive deviation between the theoretical prediction state and the data fitting state is calculated, the model cognitive deviation is compared with a preset cognitive mismatch threshold, and a mismatch discrimination result indicating cognitive mismatch or cognitive consistency is generated; the model cognitive deviation is calculated in the following manner: a difference value between the theoretical prediction state and the data fitting state is normalized by an absolute value of the data fitting state; The calculation formula of the model cognitive deviation is as follows: ； wherein, is the model cognitive bias of the moment, is the theoretical prediction state output by the physical law model module, is the data fitting state output by the data driven model module, corresponding to the same physical quantity, is a positive real constant set to prevent the denominator from being zero, whose value is much smaller than the normal measurement value, and the dimension is the same as ; the bidirectional dynamic coupling module continuously calculates using this formula; The mismatch discrimination result is judged: if the mismatch discrimination result is cognitive mismatch, a physical parameter correction amount based on a preset adaptive gain is calculated, a physical law model is updated to obtain a corrected theoretical prediction state, and the next step is entered; if the mismatch discrimination result is cognitive consistency, the next step is directly entered; State fusion is performed: if the mismatch discrimination result is cognitive consistency, the theoretical prediction state and the data fitting state are fused to generate a comprehensive evaluation result; if the mismatch discrimination result is cognitive mismatch, the corrected theoretical prediction state output by the model correction module and the data fitting state are fused to generate the comprehensive evaluation result; According to a comparison between the comprehensive evaluation result and a change trend of the comprehensive evaluation result and a preset multi-level risk threshold, an early warning information is issued, and the multi-level risk threshold includes attention, alarm and danger levels.

Images