A beidou satellite autonomous communication method based on abnormal event triggering of a ship power station

Abstract

The application discloses a Beidou satellite autonomous communication method based on abnormal event triggering of a ship power station, a novel LightGBM processing equation is designed, a three-section function is used as a correction coefficient, the non-linear characteristics of the model are effectively increased, and the overfitting phenomenon is avoided; a novel particle swarm optimization algorithm speed equation is designed, a complex nonlinear maximum-minimum coefficient term is introduced, the global optimization ability is improved, and then the optimal wavelet packet denoising layer number is determined to calculate the abnormal degree of the ship power station data; a thermal energy cooperative generative adversarial network method is proposed, the ship three-phase voltage and current are combined, the thermal energy conditions of the ship power station three-phase voltage and current are fully considered, and the data cooperative relationship of the voltage and current is effectively mined, so that whether the Beidou satellite short message communication between the ship and the shore is triggered is determined in a cooperative generative adversarial mode. The method solves the problems of limited frequency and non-autonomy of the Beidou satellite short message communication.

Description

TECHNICAL FIELD

[0001] The application relates to a Beidou satellite autonomous communication method, in particular to a Beidou satellite autonomous communication method based on abnormal events of a ship power station. BACKGROUND

[0002] Nowadays, the Beidou satellite has been widely used in the fields of space ships, vehicle traffic and geological monitoring, and it is imminent to establish a ship-shore information perception system based on Beidou satellite short message communication. However, considering the particularity of information interaction between the ocean-going ship and the remote ground command center, the Beidou satellite short message communication has the problem of limited communication frequency. When the ocean-going ship needs to communicate with the remote ground command center, the existing communication method is a time trigger mechanism, that is, non-autonomous data transmission at a fixed communication frequency, which further increases the bandwidth burden of the Beidou satellite short message communication. Therefore, in order to guarantee the efficient application of the Beidou satellite in the information situation awareness system composed of ship and shore, a Beidou satellite autonomous communication method based on abnormal events of a ship power station needs to be designed to enhance the performance of the Beidou satellite in the field of ships.

[0003] The information situation awareness system composed of ship and shore aims to transmit key shipboard data to the remote ground command center, and the judgment of the key data involved in the process is reflected in the information situation awareness of the abnormal events of the ship power station. In a single voyage, the ocean-going ship will experience multiple generator set acceleration / deceleration operations and auxiliary combined unit start / stop, and different working conditions of the power device will cause fluctuations in the voltage and current temperature of the ship power station. The frequency and amplitude of the fluctuations can be effectively obtained by the local monitoring device. In addition, when the ship power device or power system fails, it is also accompanied by random abnormal fluctuations in the voltage and current temperature curve of the ship power station, which can be effectively obtained by the shipboard sensor and situation awareness device in real time. The existing Beidou satellite short message communication method adopts a time trigger mechanism, which means that all key shipboard data need to be transmitted to the remote shore command center within each Beidou communication frequency. Considering the limited data volume and frequency of a single Beidou satellite transmission, it will lead to the problem of poor real-time performance of the remote shore command platform in the situation awareness of the ship. The time trigger mechanism cannot be applied to the information situation awareness system composed of ship and shore, which is a problem that has not been solved at present. SUMMARY

[0004] The application provides a Beidou satellite autonomous communication method based on ship power station abnormal event triggering, which can be applied to an information situation awareness system composed of a ship and a shore, guarantees efficient operation of the situation awareness system, and solves the problems of limited frequency of Beidou satellite short message communication and non-autonomous communication. Different from a ship monitoring system based on a Beidou satellite, the method of the application discards the original time-triggered communication mechanism, proposes a situation awareness algorithm based on a thermal energy synergistic generative adversarial network (TeSGAN), determines the abnormality degree by calculating the error between generated data and original data in different time periods, and triggers the Beidou satellite short message communication based on the error, which is an innovative autonomous communication method.

[0005] The purpose of the application is achieved by the following technical solutions:

[0006] A Beidou satellite autonomous communication system based on ship power station abnormal event triggering, comprising a ship power station three-phase voltage and current acquisition module, a ship power station three-phase voltage and current denoising preprocessing module, a ship power station three-phase voltage and current thermal energy input value module, a thermal energy synergistic generative adversarial network (TeSGAN) module, a ship power station multivariate data thermal energy abnormality degree calculation module, a ship power station thermal energy abnormality degree reaching a judgment threshold module, and a triggering Beidou satellite short message communication module between the ship and the shore, wherein:

[0007] The ship power station three-phase voltage and current acquisition module is responsible for real-time monitoring of ship power station three-phase voltage and current data waveforms, and segmenting the data for processing at a fixed period;

[0008] The ship power station three-phase voltage and current denoising preprocessing module is responsible for denoising preprocessing of the ship power station three-phase voltage and current acquired by the ship power station three-phase voltage and current acquisition module, removing noise in the voltage and current waveforms, and inputting the denoised data to the ship power station three-phase voltage and current thermal energy input value module;

[0009] The ship power station three-phase voltage and current thermal energy input value module is responsible for connecting with a ship power station local database, acquiring three-phase voltage and current thermal energy input values from the local database, and preprocessing lost data to complete the lost data values by using a segmented linear interpolation method;

[0010] The thermal energy synergistic generative adversarial network (TeSGAN) module is responsible for mining key data segments for triggering Beidou satellite communication;

[0011] The ship power station multivariate data thermal energy abnormality degree calculation module is responsible for calculating the thermal energy abnormality degree of the ship power station multivariate data, including the fusion abnormality degree of voltage and current;

[0012] The ship power station thermal energy abnormality degree reaching a judgment threshold module is responsible for analyzing whether the ship power station thermal energy abnormality degree reaches the set judgment threshold based on the thermal energy abnormality degree of the ship power station multi-element data. If the set judgment threshold is not reached, a new section of ship power station three-phase voltage and current values are selected for a new round of calculation. If the set judgment threshold is reached, the Beidou satellite short message communication between the ship and the shore is triggered.

[0013] The Beidou satellite short message communication module is responsible for triggering the Beidou satellite short message communication between the ship and the shore.

[0014] A Beidou satellite autonomous communication method based on ship power station abnormal event triggering using the above system, comprising the following steps:

[0015] Step one: using the ship power station three-phase voltage and current acquisition module to monitor the ship power station three-phase voltage and current data waveform in real time, and segmenting the data at a fixed period, wherein: LightGBM is used for classification processing, and the LightGBM processing equation is as follows:

[0016]

[0017] Wherein, F (t) is the current processing target, λ i is the coefficient term, is the loss expression, l represents the loss function, y i is the output value of the module, is the estimated value of the module at t-1 time, n is the data length of the three-phase voltage and current, f t represents a tree, Ω(f t ) represents the regularization term of the tree, ε is a fixed correction parameter, f t (x i ) is a new tree, The meaning is: the current prediction value is composed of the last time prediction value and the new tree;

[0018] Step two: inputting the data processed in step one into the ship power station three-phase voltage and current denoising preprocessing module to preprocess the ship power station three-phase voltage and current, removing the noise in the voltage and current waveform, and taking the denoised data as the input value of the ship power station three-phase voltage and current thermal energy input value module, wherein: the wavelet packet denoising method is used to preprocess the ship power station three-phase voltage and current, and the particle swarm optimization algorithm is designed to determine the wavelet packet layer number, and the specific equation is as follows:

[0019]

[0020] Wherein, is the particle update speed at time φ+1, is the particle update speed at time φ, r1, r2 are two different random numbers, v id is the speed value, φ is the discrete time representation, ε1, ε2 are weight coefficients, and is the extreme value, is the real position of the particle at time φ, ω max and ω min is the balance coefficient, K is the iteration maximum value, and Δ is a fixed preset value;

[0021] Step three: input the data denoised in step two into the ship power station three-phase voltage and current thermal energy input value module, pre-process the missing data, and use the piecewise linear interpolation method to complete the missing data value;

[0022] Step four: input the data processed in step three into the thermal energy collaborative generation adversarial network (TeSGAN) module to generate voltage and current thermal energy data, wherein:

[0023] The thermal energy collaborative generation adversarial network (TeSGAN) module includes a voltage thermal energy input module, a current thermal energy input module, a voltage thermal energy generator module, a current thermal energy generator module, a voltage thermal energy output module, a current thermal energy output module, a voltage thermal energy discriminator module, a current thermal energy discriminator module, and the output values of the voltage thermal energy input module and the current thermal energy input module are represented by x and y respectively; the output value of the voltage thermal energy generator module is represented by G; the output value of the current thermal energy generator module is represented by F; G1 and G2 are the output values of the voltage thermal energy generator module when the voltage and current are input respectively; F1 is the input value of the current thermal energy generator module fed back by the voltage thermal energy discriminator module, and F2 is the input value of the voltage thermal energy generator module fed back by the current thermal energy discriminator module; D1 and D2 are the discrimination results of the voltage thermal energy discriminator module and the current thermal energy discriminator module respectively, and specifically include the following processing:

[0024] L1 = Σ x [logG2(x)] + Σ y [log(2-G1(F(y)))] + Σ y [logG1(y)] + Σ x [log(1-G2(G1(x)))]

[0025] Wherein, L1 is the loss value of the generative adversarial network model without considering the thermal energy collaboration;

[0026] L2 = Σ x [||x-F(G2(x)||2] + ∑ y [||y-G(F1(y)||2]

[0027] Wherein, L2 is the increased thermal energy synergy part of the application;

[0028] L2' = Σ x [||x-F(G1(x)||2]+Σ y [||y-G(F2(y)||2]

[0029] Wherein, L2' is the increased thermal energy synergy part of the application;

[0030] L(G,F,D1,D2) = γL1 + μL2 + εL2'

[0031] Wherein, L(G,F,D1,D2) is the loss function of the thermal energy synergy generation adversarial network (TeSGAN) module, and is composed of L1, L2 and L2', and three coefficients γ, μ and ε are used as parameters to balance each subpart;

[0032]

[0033] Wherein, G * ,F * is the final optimization objective function of the thermal energy synergy generation adversarial network (TeSGAN) module, and its meaning is that the thermal energy synergy generators reach the ideal Nash equilibrium state;

[0034] Step five: input the data processed in step four into the thermal energy abnormality degree module of the ship power station multi-element data to calculate the thermal energy abnormality degree of the ship power station multi-element data, including the fusion abnormality degree of voltage and current;

[0035] Step six: input the data processed in step five into the ship power station thermal energy abnormality degree reaching decision threshold module, analyze whether the thermal energy abnormality degree of the ship power station reaches the decision threshold based on the thermal energy abnormality degree, if the thermal energy abnormality degree is greater than the decision threshold, trigger the Beidou satellite short message communication module between the ship and the shore, and perform single communication of the ship to the shore command platform, but if the thermal energy abnormality degree is less than the decision threshold, the Beidou satellite short message communication module between the ship and the shore cannot be triggered, and directly returns to the ship power station three-phase voltage and current module, selects new ship power station three-phase voltage and current values again, and performs a new round of calculation, until all the to-be-processed three-phase voltage and current thermal energy data are completely analyzed, and the whole process is ended, and finally the Beidou satellite autonomous communication based on the ship power station abnormal event triggering is realized.

[0036] Compared with the prior art, the application has the following advantages:

[0037] 1. The application can avoid the existing time triggering mechanism, and realizes autonomous communication of the Beidou satellite by using the ship power station abnormal event triggering mechanism.

[0038] 2、The application designs a new LightGBM processing equation, the correction coefficient adopts a three-section function, effectively increases the nonlinear characteristics of the model, and avoids the occurrence of overfitting.

[0039] 3、The application designs a new particle swarm optimization algorithm speed equation, by introducing a complex nonlinear maximum-minimum coefficient term, the global optimization ability is improved, and then the optimal wavelet packet denoising layer number is determined.

[0040] 4、In order to calculate the abnormal degree of ship power station data, the application proposes a thermal-energy synergistic generative adversarial network (TeSGAN) method, combines the three-phase voltage and current of the ship, fully considers the thermal energy of the three-phase voltage and current of the ship power station, and effectively mines the data synergistic relationship of the voltage and current, so as to determine whether to trigger the Beidou satellite short message communication between the ship and the shore in a synergistic generative adversarial mode. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 It is a Beidou satellite autonomous communication method based on ship power station abnormal event triggering overall structure diagram;

[0042] Figure 2 It is a thermal-energy synergistic generative adversarial network (TeSGAN) module overall structure diagram;

[0043] Figure 3 It is a ship power station three-phase voltage data waveform diagram;

[0044] Figure 4 It is a ship power station three-phase current data waveform diagram;

[0045] Figure 5 It is a ship power station three-phase voltage data abnormality discrimination result based on TeSGAN;

[0046] Figure 6 It is a ship power station three-phase current data abnormality discrimination result based on TeSGAN;

[0047] Figure 7 It is a Beidou satellite autonomous communication performance comparison diagram based on ship power station abnormal event triggering. DETAILED DESCRIPTION

[0048] The technical solutions of the application will be further described below in conjunction with the drawings, but are not limited thereto, any modification or equivalent replacement to the technical solutions of the application without departing from the spirit and scope of the application shall be covered in the protection scope of the application.

[0049] The application provides a Beidou satellite autonomous communication system triggered by an abnormal event of a ship power station. Figure 1 As shown, the system mainly comprises the following modules: a ship power station three-phase voltage and current acquisition module, a ship power station three-phase voltage and current denoising preprocessing module, a ship power station three-phase voltage and current thermal energy input value module, a thermal energy synergistic generative adversarial network (TeSGAN) module, a ship power station multivariate data thermal energy abnormality degree calculation module, a ship power station thermal energy abnormality degree reaching a judgment threshold module, and a ship-to-shore Beidou satellite short message communication triggering module. The modules are hierarchically and feedbackly fused and linked, and the abnormality degree of each data segment is judged based on a unit fixed length of data segment each time, so that the Beidou satellite autonomous communication triggered by the abnormal event of the ship power station is realized. Among them:

[0050] The ship power station three-phase voltage and current acquisition module is responsible for real-time monitoring of ship power station three-phase voltage and current data waveforms, and segmenting the data at a fixed period;

[0051] The ship power station three-phase voltage and current denoising preprocessing module is responsible for denoising preprocessing of the ship power station three-phase voltage and current collected by the ship power station three-phase voltage and current acquisition module, removing the noise in the voltage and current waveforms, and inputting the denoised data to the ship power station three-phase voltage and current thermal energy input value module;

[0052] The ship power station three-phase voltage and current thermal energy input value module is responsible for connecting with the ship power station local database, obtaining the three-phase voltage and current thermal energy input value from the local database, and, unlike the common input module, the ship power station three-phase voltage and current thermal energy input value module needs to preprocess the missing data and use the piecewise linear interpolation method to complete the missing data value;

[0053] The thermal energy synergistic generative adversarial network (TeSGAN) module is responsible for mining the key data segment triggering the Beidou satellite communication. Since the piecewise linear interpolation has barriers in processing nonlinear problems, the TeSGAN proposed in the application has very strong nonlinear characteristics and can effectively mine the key features existing in the ship power station data, providing accurate input values for the next module;

[0054] The ship power station multivariate data thermal energy abnormality degree calculation module is responsible for calculating the thermal energy abnormality degree of the ship power station multivariate data, including the fusion abnormality degree of voltage and current;

[0055] The ship power station thermal energy abnormality degree reaching a judgment threshold module is responsible for analyzing whether the ship power station thermal energy abnormality degree reaches a set judgment threshold based on the thermal energy abnormality degree of the ship power station multi-element data, if the set judgment threshold is not reached, a new section of ship power station three-phase voltage and current values are selected again for a new round of calculation, if the set judgment threshold is reached, the Beidou satellite short message communication between the ship and the shore is triggered;

[0056] The Beidou satellite short message communication between the ship and the shore triggering module is responsible for triggering the Beidou satellite short message communication between the ship and the shore.

[0057] As shown in Figure 2 The thermal energy synergistically generated adversarial network (TeSGAN) module mainly includes the following modules: a voltage thermal energy input module, a current thermal energy input module, a voltage thermal energy generator module, a current thermal energy generator module, a voltage thermal energy output module, a current thermal energy output module, a voltage thermal energy discriminator module, and a current thermal energy discriminator module, wherein:

[0058] The voltage thermal energy input module and the current thermal energy input module constitute a ship power station thermal energy synergistic input.

[0059] The voltage thermal energy input module is responsible for transmitting the ship power station three-phase voltage data to the voltage thermal energy generator module, and the generated data of the voltage thermal energy generator module is taken as the input of the voltage thermal energy output module.

[0060] The voltage thermal energy discriminator module is responsible for judging whether the error requirement is reached according to the generated value and the original value output by the voltage thermal energy output module, and feeding back the result to the voltage thermal energy generation module and the current thermal energy generation module.

[0061] The current thermal energy input module is responsible for transmitting the ship power station current thermal energy data to the current thermal energy generator module, and the generated data of the current thermal energy generator module is taken as the input of the current thermal energy output module.

[0062] The current thermal energy discriminator module is responsible for judging whether the error requirement is reached according to the generated value and the original value output by the current thermal energy output module, and feeding back the result to the current thermal energy generation module and the voltage thermal energy generation module.

[0063] The voltage thermal energy discriminator module and the current thermal energy discriminator module are combined to constitute a Nash equilibrium thermal energy synergistic discriminator, which is the key to evaluating whether the generated and adversarial results meet the error standard.

[0064] The application also provides a Beidou satellite autonomous communication method based on ship power station abnormal event triggering. Firstly, the ship power station three-phase voltage and current data waveforms are monitored in real time, and the data is segmented and processed at a fixed period. A new LightGBM is proposed for voltage / current thermal energy data classification processing. Then, the ship power station three-phase voltage and current thermal energy waveforms are denoised and pretreated. A new particle swarm optimization algorithm is designed to determine the wavelet packet layer number. Then, the denoised data is input into the Beidou satellite autonomous communication module triggered by the abnormal event. The thermal energy synergistic generative adversarial network (TeSGAN) module is the core part of the module. Then, the processed data is input into the ship power station thermal energy abnormality degree reaching the judgment threshold module. The maximum judgment threshold of the reachable abnormal degree is artificially predefined. If it is greater than the threshold, the Beidou satellite short message communication module between the ship and the shore is triggered, and the ship performs single communication to the shore command platform. If it is less than the threshold, the Beidou satellite short message communication module between the ship and the shore cannot be triggered, and is directly returned to the ship power station three-phase voltage and current module to perform a cycle process until all the three-phase voltage and current thermal energy data to be processed are completely analyzed, and the whole process is ended. Finally, the Beidou satellite autonomous communication based on the ship power station abnormal event triggering is realized. The specific steps are as follows:

[0065] Step one: the ship power station three-phase voltage and current acquisition module is used to monitor the ship power station three-phase voltage and current data waveforms in real time, and the data is segmented and processed at a fixed period. In this process, in order to effectively classify the voltage and current data, the data is segmented and processed at a fixed period. The new LightGBM of the application is used for data classification processing. The LightGBM processing equation is as follows:

[0066]

[0067] Among them, F (t) is the current processing target, λ i is the coefficient term, is the loss expression, l represents the loss function, y i is the output value of the module, is the estimated value of the module at t-1 time, n is the data length of three-phase voltage and current, f t represents a tree, Ω(f t ) represents the regularization term of the tree, and ε is a fixed correction parameter. f t (x i ) is a new tree, The meaning is: the current prediction value is composed of the last time prediction value and the new tree. The improvement of the above formula is reflected in two aspects: the λ i correction coefficient is proposed; and ε is introduced into the loss expression. Specifically, λ iis represented by a three-section function:

[0068]

[0069] where c is a fixed value, is an approaching function, p, q are the decision thresholds of the section, prob k (j) is the probability that k belongs to j, the symbol prob represents probability, k represents the kth classification type, m is the total number of categories, and max is the maximum identifier. The new three-section lambda i can effectively improve the non-linear effect of the model, avoid the occurrence of overfitting, and further realize the intelligent classification of voltage and current data.

[0070] Step two: input the data processed in step one into the ship power station three-phase voltage and current denoising preprocessing module, denoise and preprocess the ship power station three-phase voltage and current, remove the noise in the voltage and current waveform, and take the denoised data as the input value of the ship power station three-phase voltage and current thermal energy input value module.

[0071] In the process, the wavelet packet denoising method is used for denoising and preprocessing of the ship power station three-phase voltage and current.

[0072]

[0073] The position equation is not the improvement of the application, so it is not described here. The above equation is the new velocity equation proposed by the application, wherein, is the velocity of the particle updated at φ+1, is the velocity of the particle updated at φ, r1 is a random number in (0, 1), r2 is a random number in (0, 1), v id is the velocity value, φ is the discrete time representation, and ε1, ε2 are weight coefficients. and is the extreme value, is the real position of the particle at φ, ω max and ω min are the balance coefficients, K is the maximum iteration value, and Δ is a fixed preset value. The new particle swarm optimization algorithm proposed by the application can enhance the global optimization capability.

[0074] Step three: input the data denoised in step two into the ship power station three-phase voltage and current thermal energy input value module. In this process, the segmentation and classification of voltage / current have been processed in step one, and the preprocessing of voltage / current has been processed in step two, and the ship power station three-phase voltage and current thermal energy input value module needs to preprocess the missing data, and adopt the piecewise linear interpolation method to complete the missing data value.

[0075] Step four: input the data processed in step three into the thermal energy synergistic generative adversarial network (TeSGAN) module to generate voltage and current thermal energy data.

[0076] In this process, the thermal energy synergistic generative adversarial network (TeSGAN) module includes a voltage thermal energy input module, a current thermal energy input module, a voltage thermal energy generator module, a current thermal energy generator module, a voltage thermal energy output module, a current thermal energy output module, a voltage thermal energy discriminator module, and a current thermal energy discriminator module, wherein: the output values of the voltage thermal energy input module and the current thermal energy input module are represented by x and y respectively; the output value of the voltage thermal energy generator module is represented by G; the output value of the current thermal energy generator module is represented by F; G1 and G2 are the output values of the voltage thermal energy generator module when voltage and current are input respectively; F1 is the input value of the current thermal energy generator module fed back by the voltage thermal energy discriminator module, and F2 is the input value of the voltage thermal energy generator module fed back by the current thermal energy discriminator module; D1 and D2 are the discrimination results of the voltage thermal energy discriminator module and the current thermal energy discriminator module respectively, and the specific processing includes the following:

[0077] L1 = å x [logG2(x)] + å y [log(2-G1(F(y)))] + å y [logG1(y)] + å x [log(1-G2(G1(x)))]

[0078] Wherein, L1 is the loss value of the generative adversarial network model without considering the thermal energy synergy, which is composed of four parts, including: the output part of the voltage thermal energy generator module, the current thermal energy output module, the output part of the current thermal energy generator module, and the voltage thermal energy output module.

[0079] L2 = å x [||x-F(G2(x)||2] + å y [||y-G(F1(y)||2]

[0080] Wherein, L2 is the thermal energy synergy part added by the present application, which is composed of two parts, namely: the numerical result of the voltage thermal energy discriminator module input to the current thermal energy generator module, and the numerical result of the voltage thermal energy discriminator module fed back to the voltage thermal energy generator module.

[0081] L2' =∑ x [||x-F(G1(x)||2]+∑ y [||y-G(F2(y)||2]

[0082] Wherein, L2' is the added thermal energy synergy part of the application, which is composed of two parts, which are: the numerical results of the current thermal energy discriminator module input to the voltage thermal energy generator module, and the numerical results of the current thermal energy discriminator module feedback to the current thermal energy generator module.

[0083] L(G,F,D1,D2) = γL1 + μL2 + εL2'

[0084] Wherein, L(G,F,D1,D2) is the loss function of the thermal energy synergy generation adversarial network (TeSGAN) module of the application, which is composed of L1, L2 and L2', and three coefficients γ, μ and ε are used as parameters to balance each subpart.

[0085]

[0086] Wherein, G * ,F * is the final optimization objective function of the thermal energy synergy generation adversarial network (TeSGAN) module of the application, which means that the thermal energy synergy generator reaches the ideal Nash equilibrium state.

[0087] Step five: input the data processed in step four into the thermal energy abnormality degree module of the ship power station multi-element data to calculate the thermal energy abnormality degree of the ship power station multi-element data, including the fusion abnormality degree of voltage and current. In this process, the voltage and current thermal energy data generated by the thermal energy synergy generation adversarial network (TeSGAN) module are taken as the object, and the real ship three-phase voltage and current thermal energy data are taken as the benchmark. The thermal energy abnormality degree of each segmented data is calculated in the form of absolute average value.

[0088] Step six: input the data processed in step five into the ship power station thermal energy abnormality degree reaching decision threshold module, to analyze whether the ship power station thermal energy abnormality degree reaches the decision threshold based on the thermal energy abnormality degree. In this process, the maximum decision threshold that the thermal energy abnormality degree can reach is artificially predetermined, if the thermal energy abnormality degree is greater than the decision threshold, the Beidou satellite short message communication module between the ship and the shore is triggered, and single communication from the ship to the shore command platform is performed, but if the thermal energy abnormality degree is less than the decision threshold, the Beidou satellite short message communication module between the ship and the shore cannot be triggered, and directly returns to the ship power station three-phase voltage and current module, selects a new section of ship power station three-phase voltage and current value, and performs a new round of calculation, until all the three-phase voltage and current thermal energy data to be processed are completely analyzed, the whole process is ended, and the Beidou satellite autonomous communication triggered by the ship power station abnormal event is finally realized.

[0089] The present application verifies the performance of steps one to six, and uses hardware to realize the Beidou satellite autonomous communication method triggered by the ship power station abnormal event. Figure 3 The ship power station three-phase voltage data waveform diagram to be processed and the ship power station three-phase current data waveform diagram are respectively shown in the figures. Figure 4 The ship power station three-phase voltage data abnormality discrimination result based on TeSGAN and the ship power station three-phase current data abnormality discrimination result based on TeSGAN are respectively shown in the figures. Figure 5 The Beidou satellite autonomous communication performance comparison result triggered by the ship power station abnormal event is shown in the figure. Through the experimental curve and the obtained data, it can be analyzed that under the action of the Beidou satellite autonomous communication method triggered by the ship power station abnormal event designed in the present application, the thermal energy collaborative generation adversarial network (TeSGAN) module can effectively detect the abnormal data segment, and at the moment when each abnormal data segment is detected, the Beidou satellite short message communication module between the ship and the shore is triggered in real time. Compared with the Beidou short message time trigger mechanism in the prior art, the Beidou satellite autonomous communication method triggered by the ship power station abnormal event designed in the present application effectively reduces the frequency of Beidou short message communication, and further improves the communication efficiency of the Beidou satellite short message.

Claims

1. A Beidou satellite autonomous communication system triggered based on abnormal events of a ship power station, characterized in that The system comprises a ship power station three-phase voltage and current acquisition module, a ship power station three-phase voltage and current denoising preprocessing module, a ship power station three-phase voltage and current thermal energy input value module, a thermal energy collaborative generation adversarial network module, a ship power station multi-element data thermal energy abnormality degree calculation module, a ship power station thermal energy abnormality degree reaching a decision threshold module, and a ship-to-shore Beidou satellite short message communication triggering module, wherein: The ship power station three-phase voltage and current acquisition module is responsible for real-time monitoring of ship power station three-phase voltage and current data waveforms, and segmenting the data for processing at a fixed cycle; The ship power station three-phase voltage and current denoising preprocessing module is responsible for denoising preprocessing of the ship power station three-phase voltage and current collected by the ship power station three-phase voltage and current acquisition module, removing noise in the voltage and current waveforms, and inputting the denoised data to the ship power station three-phase voltage and current thermal energy input value module; The ship power station three-phase voltage and current thermal energy input value module is responsible for connecting with the ship power station local database, obtaining three-phase voltage and current thermal energy input values from the local database, and pre-processing missing data by using a segmented linear interpolation method to complete the missing data values; The thermal energy collaborative generation adversarial network module is responsible for mining key data segments triggering Beidou satellite communication; The ship power station multi-element data thermal energy abnormality degree calculation module is responsible for calculating the thermal energy abnormality degree of the ship power station multi-element data, including the fusion abnormality degree of voltage and current; The ship power station thermal energy abnormality degree reaching a decision threshold module is responsible for analyzing whether the ship power station thermal energy abnormality degree reaches the set decision threshold based on the thermal energy abnormality degree of the ship power station multi-element data, if the set decision threshold is not reached, a new segment of ship power station three-phase voltage and current values is selected for a new round of calculation, and if the set decision threshold is reached, ship-to-shore Beidou satellite short message communication is triggered; The ship-to-shore Beidou satellite short message communication triggering module is responsible for triggering ship-to-shore Beidou satellite short message communication; The output values of the voltage thermal energy input module and the current thermal energy input module are represented by respectively; the output value of the voltage thermal energy generator module is represented by ; the output value of the current thermal energy generator module is represented by ; and are the output values of the voltage thermal energy generator module when the voltage and the current are input respectively; is the input value of the voltage thermal energy discriminator module fed back to the current thermal energy generator module, is the input value of the current thermal energy discriminator module fed back to the voltage thermal energy generator module; are the discrimination results of the voltage thermal energy discriminator module and the current thermal energy discriminator module respectively, and the specific processing includes the following: wherein, is the loss value of the generative adversarial network model without considering the thermal energy synergy; wherein, is an increased first thermal energy cooperative portion; wherein, is an increased second thermal energy synergy portion; wherein, is the loss function of the thermal energy co-generated adversarial network module and three parts, using three coefficients as the parameters to balance each subpart; wherein, is the final optimization objective function of the thermal energy synergistic generation adversarial network module, which means that the thermal energy synergistic generator reaches the ideal Nash equilibrium state.

2. The Beidou autonomous communication system based on ship power station abnormal event trigger according to claim 1, characterized in that The thermal energy collaborative generation adversarial network module comprises a voltage thermal energy input module, a current thermal energy input module, a voltage thermal energy generator module, a current thermal energy generator module, a voltage thermal energy output module, a current thermal energy output module, a voltage thermal energy discriminator module, and a current thermal energy discriminator module, wherein: The voltage thermal energy input module and the current thermal energy input module constitute a ship power station thermal energy collaborative input; The voltage thermal energy input module is responsible for transmitting ship power station three-phase voltage data to the voltage thermal energy generator module, and taking the generated data of the voltage thermal energy generator module as the input of the voltage thermal energy output module; The voltage thermal energy discriminator module is responsible for judging whether the error requirement is reached according to the generated value and the original value output by the voltage thermal energy output module, and feeding back the result to the voltage thermal energy generation module and the current thermal energy generation module; The current thermal energy input module is responsible for transmitting ship power station current thermal energy data to the current thermal energy generator module, and taking the generated data of the current thermal energy generator module as the input of the current thermal energy output module; The current thermal energy discriminator module is responsible for judging whether the error requirement is reached according to the generated value and the original value output by the current thermal energy output module, and feeding back the result to the current thermal energy generation module and the voltage thermal energy generation module; The voltage thermal energy discriminator module and the current thermal energy discriminator module are combined to form a Nash equilibrium thermal energy collaborative discriminator to evaluate whether the generation and confrontation results meet the error standard.

3. A method for implementing autonomous communication of Beidou satellite based on abnormal events of ship power station triggering by using the system of any one of claims 1-2, characterized in that The method comprises the following steps: Step one: real-time monitoring of ship power station three-phase voltage and current data waveform by using ship power station three-phase voltage and current acquisition module, and segmenting the data for processing at a fixed period; Step two: inputting the data processed in step one into the ship power station three-phase voltage and current denoising preprocessing module for denoising preprocessing of the ship power station three-phase voltage and current, removing the noise in the voltage and current waveform, and taking the denoised data as the input value of the ship power station three-phase voltage and current thermal energy input value module; Step three: inputting the denoised data in step two into the ship power station three-phase voltage and current thermal energy input value module for preprocessing of missing data, and using the piecewise linear interpolation method to complete the missing data value; Step four: inputting the data processed in step three into the thermal energy collaborative generation confrontation network module to generate voltage and current thermal energy data, and the specific steps are as follows: The output values of the voltage thermal energy input module and the current thermal energy input module are represented by and respectively; the output value of the voltage thermal energy generator module is represented by The output value of the current thermal energy generator module is represented by ; and are the voltage and current, respectively, as input to the voltage thermal energy generator module output value; is the input value of the voltage thermal energy discriminator module fed back to the current thermal energy generator module, is the input value of the current thermal energy discriminator module fed back to the voltage thermal energy generator module; are the discrimination results of the voltage thermal energy discriminator module and the current thermal energy discriminator module, respectively, and specifically include the following processing: wherein, is the loss value of the generative adversarial network model without considering the synergy of thermal energy. wherein, is an increased first thermal energy cooperative portion; wherein, is an increased second thermal energy synergy portion; wherein, is the loss function of the thermal energy co-generated adversarial network module and three parts, using three coefficients as the parameters to balance each subpart; wherein, is the final optimization objective function of the thermal energy synergistic generation adversarial network module, which means that the thermal energy synergistic generator reaches the ideal Nash equilibrium state; Step five: inputting the data processed in step four into the thermal energy abnormality degree module for calculating the thermal energy abnormality degree of the ship power station multi-element data, including the fusion abnormality degree of voltage and current; Step six: inputting the data processed in step five into the ship power station thermal energy abnormality degree reaching decision threshold module to analyze whether the ship power station thermal energy abnormality degree reaches the decision threshold based on the thermal energy abnormality degree, if the thermal energy abnormality degree is greater than the decision threshold, triggering the Beidou satellite short message communication module between the ship and the shore, and performing single communication of the ship to the shore command platform, but if the thermal energy abnormality degree is less than the decision threshold, the Beidou satellite short message communication module between the ship and the shore cannot be triggered, and directly returns to the ship power station three-phase voltage and current module to select new ship power station three-phase voltage and current values for a new round of calculation, until all the three-phase voltage and current thermal energy data to be processed are completely analyzed, then the whole process is ended, and finally the Beidou satellite autonomous communication based on the ship power station abnormal event triggering is realized.

4. The ship power station abnormal event triggered Beidou satellite autonomous communication method according to claim 3, characterized in that In step one, LightGBM is used for classification processing of data, and the LightGBM processing equation is as follows: wherein, is the processing target at the current time, is the coefficient term, is the loss expression, represents the loss function, is the output value of the module, is the estimated value of the module at the time, is the data length of the three-phase voltage and current, denotes a tree, denotes the regularization term of the tree, is a fixed correction parameter, is a new tree, the meaning is that the prediction value at the current time is composed of the prediction value at the last time and the new tree.

5. The ship power station abnormal event triggered Beidou satellite autonomous communication method according to claim 4, characterized in that The is represented by a three-segment function: wherein is a constant value, is an approaching function, is a piecewise decision threshold, is is the probability that a sample belongs to class denotes the probability, denotes the th class type, is the total number of classes, and max is the maximum identifier.

6. The ship power station abnormal event triggered Beidou satellite autonomous communication method according to claim 3, characterized in that In step two, the wavelet packet denoising method is used for denoising preprocessing of the ship power station three-phase voltage and current, and a particle swarm optimization algorithm is designed to determine the wavelet packet layer number, and the specific equation is as follows: wherein is the speed of the particle update at time is the speed of the particle update at time are two different random numbers, respectively, is a speed value, is a discretized time representation, is a weight coefficient, and is an extreme value, is the real position of the particle at time and is a balancing coefficient, is an iteration maximum value, is a fixed preset value.

Images