A communication adaptive control method, device, and equipment based on underwater acoustic environment

Abstract

The present invention provides a communication adaptive control method, device and equipment based on an underwater acoustic environment. First, a prediction model is trained based on the acquired signal bit error rate data corresponding to a plurality of different communication system signals and the underwater acoustic environment data in which the communication system signals are transmitted; then, the underwater acoustic environment data in which the communication system signals are transmitted is input into the prediction model to obtain signal bit error rate prediction data; finally, according to the signal bit error rate prediction data, a suitable communication system is selected for signal transmission. According to the above method, a suitable communication system can be predicted and selected for underwater acoustic communication according to changes in the underwater acoustic environment, so as to improve the reliability of underwater acoustic communication.

Description

Technical Field

[0001] The present invention relates to the field of underwater acoustic communication technology, and in particular to a communication adaptive control method, device and equipment based on an underwater acoustic environment. Background Art

[0002] The underwater acoustic environment changes over time, especially in summer, when the changes are more complex and drastic. Changes in the underwater acoustic environment will affect the reliability of underwater acoustic communications, and having the ability to adapt to the environment is a requirement and goal of underwater acoustic communication equipment. Existing research on adaptive methods for underwater acoustic communications generally focuses on methods applicable to a single communication system, such as adaptive coding, adaptive equalization, adaptive Doppler compensation, and adaptive frequency hopping; methods applicable to different communication systems generally use closed-loop adaptive control methods, which require the receiver to feedback parameters such as signal-to-noise ratio and channel structure as the basis for adaptive adjustment. In actual use, a single communication system may not be able to adapt to drastic changes in the underwater acoustic environment; and the use of closed-loop control methods may cause the transmitter to be unable to correctly receive feedback from the receiver due to the influence of the underwater acoustic environment, thereby rendering the above method invalid.

[0003] Therefore, it is necessary to provide an open-loop adaptive control method for underwater acoustic communication that is applicable to a variety of communication systems in order to improve the reliability of underwater acoustic communication. Summary of the invention

[0004] The present invention describes a communication adaptive control method, device and equipment based on underwater acoustic environment, which can solve the above technical problems.

[0005] According to a first aspect, a communication adaptive control method based on an underwater acoustic environment is provided, the method comprising:

[0006] The prediction model is trained based on the acquired signal bit error rate data corresponding to the signals of various different communication systems and the underwater acoustic environment data in which the communication system signals are transmitted; wherein the number of the prediction models may be one or more;

[0007] Input the underwater acoustic environment data of the communication system signal when it is transmitted into the prediction model to obtain the signal bit error rate prediction data;

[0008] According to the signal bit error rate prediction data, select the appropriate communication system for signal transmission.

[0009] In some embodiments, the communication rates of the different types of communication scheme signals are different, and the communication rate of each communication scheme signal is constant.

[0010] In some embodiments, a method for obtaining signal bit error rate data corresponding to a plurality of different communication system signals and underwater acoustic environment data in which the communication system signals are transmitted specifically includes:

[0011] Deploy a transceiver for underwater acoustic communication in the waters where communication is required; the transceiver includes a signal transmitting end and a signal receiving end;

[0012] The signal transmitting end transmits a communication signal to the signal receiving end; at the same time, a water acoustic environment measuring device is placed at the signal transmitting end to obtain water acoustic environment data, wherein the water acoustic environment data specifically includes: sound velocity profile, wind speed and direction, flow velocity and direction, background noise, transducer depth, etc.;

[0013] The communication signal transmitted by the transmitting end is received at the signal receiving end, recorded and decoded to obtain the signal bit error rate data.

[0014] In some embodiments, after acquiring the underwater acoustic environment data, the sound velocity profile data therein is simplified, and the simplified data includes: thermocline temperature difference, thermocline depth, average gradient, etc.

[0015] In some embodiments, the prediction model used is a neural network model and / or a pseudo-inverse matrix prediction model.

[0016] In some embodiments, the method of selecting a suitable communication system signal includes: selecting a communication system with the lowest bit error rate; or selecting a communication system with the highest communication rate from communication systems with bit error rates lower than a preset minimum threshold.

[0017] In some embodiments, when there are multiple prediction models, the prediction results of the models can be compared with the actual data, and based on the comparison results, a suitable model can be selected to predict subsequent data.

[0018] According to a second aspect, a communication adaptive control device based on an underwater acoustic environment is provided, the device comprising:

[0019] A data acquisition module, used to acquire underwater acoustic environment data and signal bit error rate data;

[0020] Model building module, used to build prediction models;

[0021] Model training module, used to train underwater acoustic environment data and signal bit error rate data;

[0022] A model output module is used to receive underwater acoustic environment data and output signal bit error rate prediction data;

[0023] The communication system selection module is used to select a suitable communication system for signal transmission according to the signal bit error rate prediction data.

[0024] In one embodiment, the data acquisition module further includes a signal transceiver, and the signal transceiver includes:

[0025] A signal transmitting end, used for transmitting a communication signal to a signal receiving end;

[0026] The underwater acoustic environment measuring device is placed at the signal transmitting end and is used to monitor the underwater acoustic environment and obtain underwater acoustic environment data;

[0027] The signal receiving end is used to receive the communication signal transmitted by the signal transmitting end, perform bit error rate detection, and obtain signal bit error rate data.

[0028] According to a third aspect, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and wherein the processor implements any method described in the first aspect when executing the computer program.

[0029] The present invention provides a communication adaptive control method, device and equipment based on an underwater acoustic environment. The prediction model is trained by using underwater acoustic environment data and signal bit error rate data, and then the underwater acoustic environment data is input into the trained prediction model to predict the signal bit error rate, and finally a suitable communication system is selected for signal transmission according to the signal bit error rate prediction data. According to the above method, a suitable communication system can be predicted and selected for underwater acoustic communication according to changes in the underwater acoustic environment, so as to improve the reliability of underwater acoustic communication. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 A flow chart of a communication adaptive control method based on an underwater acoustic environment provided in an embodiment of this specification is shown;

[0032] Figure 2 A schematic diagram of a communication system prediction model training provided by an embodiment of this specification is shown;

[0033] Figure 3 The figure shows the change of the sound velocity profile of the transmitting end for 24 consecutive hours provided in the embodiment of this specification;

[0034] Figure 4 A continuous 24-hour wind speed and flow velocity variation diagram provided in the embodiment of this specification is shown;

[0035] Figure 5 A graph showing the change in normalized background noise for 24 consecutive hours provided in the embodiments of this specification is shown;

[0036] Figure 6A graph showing the depth variation of the continuous 24-hour emission transducer provided in the embodiment of this specification is shown;

[0037] Figure 7 The highest level image showing correct decoding of 720 groups of signals at the receiving end provided by the embodiment of this specification;

[0038] Figure 8 A schematic diagram of a communication adaptive control device based on an underwater acoustic environment provided in an embodiment of this specification is shown;

[0039] Fig. 9 A schematic diagram of a signal transceiver device provided in an embodiment of this specification is shown. DETAILED DESCRIPTION

[0040] The solution provided in this specification is described below in conjunction with the accompanying drawings.

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0042] In the description of the embodiments of the present application, words such as "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a concrete way.

[0043] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the term "plurality" means two or more.

[0044] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprises", "has" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0045] Before describing the technical solution of the present application, it is necessary to explain the basic principles involved in the solution.

[0046] Bit Error Rate:

[0047] It is one of the important indicators to measure the performance of data communication systems. It indicates the ratio of the number of erroneous bits received during data transmission to the total number of transmitted bits. The bit error rate provides direct information about the reliability of data transmission and is an important basis for evaluating the quality of communication links, modulation and demodulation technology, channel coding efficiency and the effectiveness of receiver design.

[0048] The relationship between decoding accuracy (inversely proportional to bit error rate) and communication rate:

[0049] As communication rates increase, the signal spectrum width usually increases to accommodate more data, which may lead to energy dispersion, causing the signal power within a unit frequency band to decrease, making it more susceptible to noise interference, and the decoding accuracy will decrease accordingly.

[0050] Figure 1 A flow chart of a communication adaptive control method based on an underwater acoustic environment provided by an embodiment of this specification is shown. Figure 1 As shown, the method comprises the following steps:

[0051] Step S101, training a prediction model based on the acquired bit error rate data corresponding to the signals of multiple different communication systems and the underwater acoustic environment data in which the communication system signals are transmitted; wherein the number of the prediction models can be one or more (this step can be referred to Figure 2 ).

[0052] First, it is necessary to obtain the signal bit error rate data corresponding to a variety of different communication system signals and the underwater acoustic environment data when the communication system signal is transmitted. Secondly, select the constructed prediction model. The number of the prediction models can be one or more. The selection of the prediction model can be changed according to the changes in data and environment, and there is no restriction here. Then, the obtained signal bit error rate data corresponding to a variety of different communication system signals and the underwater acoustic environment data when the communication system signal is transmitted are input into the prediction model for training. After multiple cycles, a prediction model that meets the user's requirements is obtained.

[0053] In some embodiments, the communication rates of the different types of communication scheme signals are different, and the communication rate of each communication scheme signal is constant.

[0054] According to the industry standards and protocols of underwater acoustic communication, a variety of different communication systems are selected. The significant difference between these systems is reflected in the different communication rates they provide. However, once a communication system is determined, the signal transmission rate in the underwater environment remains relatively constant to ensure the stability and reliability of communication.

[0055] In some embodiments, the method of obtaining signal bit error rate data corresponding to a plurality of different communication system signals and underwater acoustic environment data when the communication system signals are transmitted includes:

[0056] Step S1011, deploying a transceiver for underwater acoustic communication in the waters where communication is required; the transceiver includes a signal transmitting end and a signal receiving end.

[0057] The signal transmitting device of the communication system is deployed at a suitable position under the water surface of the target waters. Then, based on the position of the transmitting end, an appropriate distance is calculated and selected to ensure good signal propagation and reflect the characteristics of the actual communication scenario. The signal receiving end is deployed based on this distance.

[0058] Exemplarily, the transmitting end and the receiving end are respectively deployed at two locations 8 km apart below the horizontal surface of the target water area where communication is required.

[0059] Step S1012, the signal transmitting end transmits a communication signal to the signal receiving end; at the same time, a water acoustic environment measuring device is placed at the signal transmitting end to obtain water acoustic environment data, wherein the water acoustic environment data specifically includes: sound velocity profile, wind speed and direction, flow velocity and direction, background noise, transducer depth, etc.;

[0060] A plurality of selected communication signals of different communication systems are transmitted from a signal transmitting end to a signal receiving end.

[0061] Exemplarily, three different communication systems are selected, including: m-sequence spread spectrum with a center frequency of 6 kHz (DSSS 6), m-sequence spread spectrum with a center frequency of 10 kHz (DSSS10) and GOLD code spread spectrum with a center frequency of 6 kHz (GOLD 6), and they are sorted in order of communication rate from high to low, namely: GOLD 6>DSSS10>DSSS 6, respectively recorded as gear 3, gear 2 and gear 1. The communication system signals of these three gears are transmitted in turn, and the three communication system signals are transmitted once within 2 minutes. After the three communication system signals are transmitted within 2 minutes, they are recorded as a group of data. The signals of the three gears are transmitted 720 times each for 24 consecutive hours, and a total of 720 groups of data are recorded.

[0062] A hydroacoustic environment measuring device is placed at the signal transmitting end. While the signal transmitting end transmits the communication signal, the hydroacoustic environment measuring device collects the corresponding hydroacoustic environment data. The hydroacoustic environment data includes: sound velocity profile, wind speed and direction, flow velocity and direction, background noise, transducer depth, etc.

[0063] For example, while the signal transmitting end transmits signals of three different communication systems, GOLD 6, DSSS10, and DSSS 6, to the signal receiving end, the sound velocity profile data (such as Figure 3), wind speed and direction data (such as Figure 4 ), flow velocity and direction data (such as Figure 4 ), background noise data (such as Figure 5 as shown), transducer depth data (as shown Figure 6 shown).

[0064] In one embodiment, after acquiring the underwater acoustic environment data, the sound velocity profile data therein is simplified, and the simplified data includes: thermocline temperature difference, thermocline depth, average gradient, etc.

[0065] In the actual sound velocity profile data obtained, there is a large amount of data, which is not conducive to model training. In order to better adapt to the model training, in this embodiment, it is considered to simplify the sound velocity profile into data such as thermocline temperature difference, thermocline depth, average gradient, etc., and the simplification process includes:

[0066] Based on the empirical formula for converting the speed of sound at different depths d and the water temperature temp at that depth, it is as follows:

[0067] speed=1449.2+4.6×temp-0.055×temp 2 +(1.34-0.01×temp)×(33.84-s)+0.016×d

[0068] In the formula,

[0069] S represents the salinity of seawater in thousandths, which can generally be taken as 35;

[0070] speed is expressed as the speed of sound;

[0071] temp represents the water temperature;

[0072] d represents the depth value;

[0073] Therm_Diff is the maximum absolute value of the temperature difference between adjacent depths, and its calculation method is:

[0074] Therm_Diff=max(abs(temp d+1 -temp d )),d=1,2,…,D-1

[0075] Among them, temp d is the temperature value at depth d; temp d+1 is the temperature value at the depth adjacent to depth d.

[0076] The thermocline depth Therm_Depth is recorded as the depth value d+1 where the thermocline temperature difference Therm_D i ff is located.

[0077] The average gradient Avarage_Di ff refers to the average value of the temperature difference between adjacent depths, which is calculated as follows:

[0078] Avarage_Diff=∑ d (abs(temp d+1 –temp d )) / (D-1),d=1,2,…,D-1

[0079] Given the high complexity of the actual sound velocity profile data collected, directly applying it to the prediction model training may lead to a shortage of model computing resources and a significant extension of the training cycle, thus affecting the model's ability to make rapid predictions. To solve this problem, data dimensionality reduction can be used to simplify the complex sound velocity profile data into a few key parameters. This not only effectively reduces the model's computational burden and shortens the training time, but also retains the main information that affects the propagation of sound waves, ensuring the accuracy and practicality of the model prediction, and achieving an optimal balance between model efficiency and prediction effect.

[0080] Step S1013, receiving the communication signal transmitted by the transmitting end at the signal receiving end, recording and decoding it to obtain signal bit error rate data.

[0081] After receiving the communication signal, the signal receiving end will record and decode it. After decoding, the receiving end will compare the decoded data with the original data, count the differences between the two data, and record the number of error bits. The ratio of the number of error bits to the total number of bits is the signal bit error rate.

[0082] For example, after receiving the data of three different communication systems, GOLD 6, DSSS10, and DSSS 6, transmitted from the signal transmitting end, the signal receiving end records and decodes the data to obtain 720 sets of bit error rate data (see Figure 7 ).

[0083] It should be noted that this embodiment stipulates that the error rate must be lower than a certain threshold to indicate that the signal receiving end decodes the signal correctly. The threshold is specified as 0.001. In addition, the accuracy of signal decoding is related to the communication rate of the signal. The higher the communication rate, the lower the accuracy of its decoding. Sorting in order from high to low communication rate, in turn: GOLD 6 (3rd gear) > DSSS 10 (2nd gear) > DSSS 6 (1st gear). Thus, sorting in order from high to low decoding accuracy, in turn: DSSS 6 (1st gear) > DSSS10 (2nd gear) > GOLD 6 (3rd gear). On this basis, we use the following logic to record the decoding situation: If the 3rd gear (GOLD 6) with the fastest communication rate can be successfully decoded, it is assumed that the signals of 2nd gear (DSSS10) and 1st gear (DSSS6) can also be correctly decoded. At this time, the highest correct decoding gear recorded is 3. If the decoding of the 3rd gear signal fails, but the 2nd gear signal can be correctly decoded, the 1st gear signal is also regarded as correctly decoded. At this time, the highest correct decoding gear is recorded as 2. Finally, if both the 3rd and 2nd gear signals are decoded incorrectly, and only the 1st gear signal is decoded successfully, then the highest decoded correct gear is recorded as 1. The above explanations can be referred to in Table 1.

[0084] Communication system / number of data groups 1 group 2 groups 3 groups 4 groups 5 groups …… 720 groups GOLD 6 (3 gears) √ √ √ √ DSSS10(2 gears) √ DSSS 6 (1st gear) √

[0085] Table 1

[0086] In some embodiments, the prediction model used is a neural network model and / or a pseudo-inverse matrix prediction model.

[0087] When the selected prediction model is a neural network model, the neural network model is trained by utilizing the acquired signal bit error rate data corresponding to a variety of different communication system signals and the underwater acoustic environment data in which the communication system signals are transmitted.

[0088] Exemplarily, a total of 720 sets of data are collected, and the underwater acoustic environment data and signal error rate data in the first 60 sets of data are used as training data. The training data are classified according to three communication systems: DSSS 6, DSSS10, and GOLD 6, and the neural network model is trained respectively. Furthermore, the neural network model selects a generalized radial basis function neural network (GRNN), and the trained generalized radial basis function neural network (GRNN) model is recorded as GRNN_ALL.

[0089] When the selected prediction model is the pseudo-inverse matrix initial model, the pseudo-inverse matrix prediction model is trained by using the acquired signal bit error rate data corresponding to the signals of various different communication systems and the underwater acoustic environment data when the communication system signals are transmitted. The training process of the pseudo-inverse matrix prediction model includes:

[0090] Step S1014, constructing a pseudo-inverse matrix prediction model using the PI NV function, underwater acoustic environment data of a variety of different communication systems, and signal bit error rate data.

[0091] For each communication system, a feature matrix X is constructed using the underwater acoustic environment data. i , use the signal bit error rate data to construct a target variable vector Y i Then, the pseudo-inverse matrix PINV (X i ), as follows:

[0092] W i =PINV(X i )@Y i

[0093] Among them, W i represents the weight vector; PINV(X i ) represents the pseudo-inverse matrix; @ represents matrix multiplication; Y i represents the target variable vector; X i Represents the feature matrix.

[0094] Step S1015, training a pseudo-inverse matrix prediction model by using the acquired signal bit error rate data corresponding to the signals of various different communication systems and the underwater acoustic environment data in which the communication system signals are transmitted.

[0095] The underwater acoustic environment data and signal bit error rate data corresponding to each communication system signal are input into the pseudo-inverse matrix prediction model constructed in step S1014, and the model is trained. The trained model is shown as follows:

[0096] y^ new =W i ·x^ new

[0097] In the formula, x^ new Represents the pre-input water acoustic environment data; y^ new Represents the predicted bit error rate data;

[0098] The underwater acoustic environment data and the signal bit error rate data can be divided into two parts. The first part of the data is used to train the initial model of the pseudo-inverse matrix, and the second part of the data is used to test the trained pseudo-inverse matrix prediction model.

[0099] Exemplarily, a total of 720 sets of data are collected, and the underwater acoustic environment data and signal bit error rate data in the first 60 sets of data are used as training data. The training data are classified according to three communication systems: DSSS 6, DSSS10, and GOLD 6. The pseudo-inverse matrix prediction models are trained respectively, and the trained pseudo-inverse matrix prediction model is recorded as PI NV_ALL.

[0100] The advantages of using the pseudo-inverse matrix prediction model are: its computational complexity is low, and the results can be obtained directly through matrix operations without multiple iterative training; in addition, since the pseudo-inverse matrix method is based on linear relationships to establish a model, its results are often easier to explain, and the contribution of each feature to the prediction result can be directly seen through the model coefficient, which is conducive to understanding and analyzing the importance of the feature.

[0101] When the prediction models selected are the neural network model and the pseudo-inverse matrix prediction model, the neural network model and the pseudo-inverse matrix prediction model are trained by using the acquired signal bit error rate data corresponding to the signals of various different communication systems and the underwater acoustic environment data in which the communication system signals are transmitted. It is easy to understand that the process of training the neural network model and the pseudo-inverse matrix prediction model repeats the training process described in the above two examples, and will not be repeated here.

[0102] In other embodiments, the prediction model is trained using simplified sound velocity profile data (ie, data on thermocline temperature difference, thermocline depth, average gradient, etc.) and signal error rate data.

[0103] When the selected prediction model is a neural network model, the streamlined sound velocity profile data (i.e., jump layer temperature difference, jump layer depth, average gradient and other data) and signal bit error rate data are divided into two parts. The first part of the data is used to train the neural network model, and the second part of the data is used to test the trained neural network model.

[0104] Exemplarily, a total of 720 sets of data are collected, and the streamlined sound velocity profile data (i.e., jump layer temperature difference, jump layer depth, average gradient and other data) and signal bit error rate data in the first 60 sets of data are used as training data. The training data are classified according to three communication systems: DSSS 6, DSSS10, and GOLD 6, and the neural network is trained separately. The neural network model uses a generalized radial basis function neural network (GRNN), and the trained generalized radial basis function neural network (GRNN) model is recorded as GRNN_PART.

[0105] When the selected prediction model is the pseudo-inverse matrix prediction model, the streamlined sound velocity profile data (i.e., jump layer temperature difference, jump layer depth, average gradient and other data) and signal bit error rate data are divided into two parts. The first part of the data is used to train the pseudo-inverse matrix prediction model, and the second part of the data is used to test the trained pseudo-inverse matrix prediction model.

[0106] Exemplarily, a total of 720 sets of data are collected, and the streamlined sound velocity profile data (i.e., jump layer temperature difference, jump layer depth, average gradient and other data) and signal bit error rate data in the first 60 sets of data are used as training data. The training data are classified according to three communication systems: DSSS 6, DSSS10, and GOLD 6, and the pseudo-inverse matrix initial models are trained respectively. The trained pseudo-inverse matrix prediction model is recorded as PI NV_PART.

[0107] When the prediction model selected is a neural network model and a pseudo-inverse matrix prediction model, the neural network model and the pseudo-inverse matrix prediction model are trained by using the simplified sound velocity profile data (i.e., thermocline temperature difference, thermocline depth, average gradient, etc.) and signal bit error rate data corresponding to each communication system signal. It is easy to understand that the process of training the neural network model and the pseudo-inverse matrix prediction model is repeated with the training process described in the above two examples, and will not be repeated here.

[0108] Step S102, inputting the underwater acoustic environment data in which the communication system signal is transmitted into the prediction model to obtain signal bit error rate prediction data.

[0109] In some embodiments, the second portion of the underwater acoustic environment data is used to test the trained neural network model.

[0110] Exemplarily, a total of 720 groups of data are collected, and the underwater acoustic environment data in the 61st to 720th groups of data are used as test data. The test data are classified according to three communication systems: DSSS 6, DSSS10, and GOLD 6. The trained neural network model GRNN_ALL is tested respectively to obtain the corresponding signal bit error rate prediction data.

[0111] In some embodiments, the second part of the streamlined sound velocity profile data (ie, data such as thermocline temperature difference, thermocline depth, average gradient, etc.) is used to test the trained neural network model.

[0112] Exemplarily, a total of 720 groups of data are collected, and the streamlined sound velocity profile data (i.e., jump layer temperature difference, jump layer depth, average gradient and other data) in the 61st to 720th groups of data are used as test data. The test data are classified according to the three communication systems of DSSS 6, DSSS10, and GOLD 6, and the trained neural network model GRNN_PART is tested respectively to obtain the corresponding signal bit error rate prediction data.

[0113] In some embodiments, the second portion of the underwater acoustic environment data is used to test the trained pseudo-inverse matrix prediction model.

[0114] Exemplarily, a total of 720 groups of data are collected, and the underwater acoustic environment data in the 61st to 720th groups of data are used as test data. The test data are classified according to three communication systems: DSSS 6, DSSS10, and GOLD 6. The trained pseudo-inverse matrix prediction model PI NA_ALL is tested respectively to obtain the corresponding signal bit error rate prediction data.

[0115] In some embodiments, the second part of the streamlined sound velocity profile data (ie, data such as thermocline temperature difference, thermocline depth, average gradient, etc.) is used to test the trained pseudo-inverse matrix prediction model.

[0116] Exemplarily, a total of 720 groups of data are collected, and the streamlined sound velocity profile data (i.e., jump layer temperature difference, jump layer depth, average gradient and other data) in the 61st to 720th groups of data are used as test data. The test data are classified according to three communication systems: DSSS 6, DSSS10, and GOLD 6. The trained pseudo-inverse matrix prediction model PI NA_PART is tested respectively to obtain the corresponding signal bit error rate prediction data.

[0117] Step S103: selecting a suitable communication system for signal transmission according to the signal bit error rate prediction data.

[0118] In one embodiment, a communication system signal with the lowest bit error rate in the prediction results may be selected for signal transmission.

[0119] For example, in a set of data prediction results, the bit error rates of the three communication systems DSSS 6, DSSS10, and GOLD 6 are respectively 0.0004, 0.0003, and 0.0002. The bit error rate of the communication system GOLD 6 is the lowest, and the communication system GOLD 6 can be selected for signal transmission.

[0120] In one embodiment, the communication system with the highest communication rate may be selected from the communication systems with bit error rates lower than a preset minimum threshold.

[0121] For example, assuming that the minimum bit error rate threshold is 0.001, the prediction results of a set of data show that the bit error rates of the three communication systems DSSS 6, DSSS10, and GOLD 6 are 0.0002, 0.0003, and 0.0004 respectively. The bit error rates of the three communication systems are all lower than the minimum bit error rate threshold. Then, the communication system signal with the highest communication rate is further selected. The communication rates of these three communication systems are arranged from large to small, which is: DSSS 6>DSSS10>GOLD 6. Then, the communication system DSSS 6 with the highest communication rate is selected for signal transmission.

[0122] In one embodiment, when there are multiple prediction models, the prediction results of the models may be compared with the actual data, and based on the comparison results, a suitable model may be selected to predict subsequent data.

[0123] Exemplarily, four prediction models GRNN_ALL, GRNN_PART, PI NV_ALL, and PI NV_PART are used to compare the prediction results in the 61st to 720th groups of data with the actual data. The comparison results are shown in Table 2, where GOOD represents the ratio of the number of correct predictions made by the prediction model for the communication system with the lowest bit error rate to the actual number of data (i.e., 660); BEST represents the ratio of the number of correct predictions made by the prediction model for the communication system with the highest communication rate and below the minimum bit error rate threshold (i.e., 0.001) to the actual number of data (i.e., 660).

[0124]

[0125] Table 2 Comparison of the number of data correctly predicted by the model and the actual number of data

[0126] After comparison, it is found that the correct proportion of GOOD prediction results of PI NV prediction model is slightly higher than that of GRNN prediction model, but there is a big gap in the correct proportion of BEST prediction results; the correct proportion of GOOD prediction results of PART parameter method (i.e., the method of training the model with streamlined sound velocity profile data) is not much different from that of ALL parameter method (i.e., the method of training the model with underwater acoustic environment data), and the correct proportion of BEST prediction results is slightly lower than that of ALL parameter method; in terms of computational complexity, GRNN_ALL>GRNN_PART>>PI NV_ALL>PI NV_PART. In actual use, the appropriate prediction model can be selected according to needs.

[0127] Corresponding to the above method provided by the present invention, the present invention also provides a device. Figure 8 FIG. 2 shows a schematic diagram of a communication adaptive control device based on an underwater acoustic environment provided by an embodiment of this specification. Figure 8As shown, the device comprises:

[0128] The data acquisition module 801 is used to acquire underwater acoustic environment data and signal bit error rate data;

[0129] A model building module 802 is used to build a prediction model;

[0130] Model training module 803, used for training the underwater acoustic environment data and signal bit error rate data;

[0131] The model output module 804 is used to receive the underwater acoustic environment data and output the predicted bit error rate data;

[0132] The communication system selection module 805 is used to select a suitable communication system for signal transmission according to the predicted bit error rate data.

[0133] In one embodiment, the data acquisition module includes a signal transceiver, and the signal transceiver 900 specifically includes:

[0134] The signal transmitting end 901 is used to transmit a communication signal to the signal receiving end;

[0135] The underwater acoustic environment measuring device 902 is placed at the signal transmitting end and is used to detect the underwater acoustic environment and obtain the underwater acoustic environment data;

[0136] The signal receiving end 903 is used to receive the communication signal transmitted by the signal transmitting end, and perform bit error rate detection to obtain bit error rate data.

[0137] It is worth mentioning that Figure 8 The device shown is Figure 1 The method embodiments shown correspond to and can be applied to Figure 1 The acquisition of underwater acoustic environment data and signal bit error rate data, construction of prediction model, training of prediction model, output of bit error rate prediction results and selection of appropriate communication system for signal transmission in the illustrated method embodiment will not be described in detail here. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0138] According to another embodiment of the present invention, a computing device is provided, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the Figure 1 The method described.

[0139] According to another embodiment, there is also provided a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute a combination of Figure 1 The method described.

[0140] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, firmware or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0141] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A communication adaptive control method based on underwater acoustic environment, characterized in that: The method comprises: A prediction model is trained based on the acquired signal bit error rate data corresponding to a plurality of different communication system signals and the underwater acoustic environment data in which the communication system signals are transmitted; wherein the number of the prediction models may be one or more; a method for acquiring the signal bit error rate data corresponding to a plurality of different communication system signals and the underwater acoustic environment data in which the communication system signals are transmitted specifically comprises: Deploy a transceiver for underwater acoustic communication in the waters where communication is required; the transceiver includes a signal transmitting end and a signal receiving end; The signal transmitting end transmits a communication signal to the signal receiving end; at the same time, an underwater acoustic environment measuring device is placed at the signal transmitting end to obtain underwater acoustic environment data; The communication signal transmitted by the transmitting end is received at the signal receiving end, recorded and decoded to obtain signal bit error rate data; Input the underwater acoustic environment data of the communication system signal when it is transmitted into the prediction model to obtain the signal bit error rate prediction data; According to the signal bit error rate prediction data, select the appropriate communication system for signal transmission.

2. The method according to claim 1, characterized in that The communication rates of the plurality of different communication scheme signals are different, and the communication rate of each communication scheme signal is constant.

3. The method according to claim 1, characterized in that The underwater acoustic environment data specifically includes: sound velocity profile, wind speed and direction, flow velocity and direction, background noise, and transducer depth.

4. The method according to claim 3, characterized in that: After acquiring the underwater acoustic environment data, the sound velocity profile data is simplified. The simplified data includes: thermocline temperature difference, thermocline depth, and average gradient.

5. The method according to claim 1, characterized in that The prediction model used is a neural network model and / or a pseudo-inverse matrix prediction model.

6. The method according to claim 1, characterized in that The method of selecting a suitable communication system includes: selecting a communication system with the lowest bit error rate; or selecting a communication system with the highest communication rate from communication systems with bit error rates lower than a preset minimum threshold.

7. The method according to claim 1, characterized in that When there are multiple prediction models, the prediction results of the models can be compared with the actual data, and based on the comparison results, a suitable prediction model can be selected to predict subsequent data.

8. A communication adaptive control device based on underwater acoustic environment, characterized in that: The method according to any one of claims 1 to 7 is used to select a suitable communication system for signal transmission, wherein the device comprises: A data acquisition module, used to acquire underwater acoustic environment data and signal bit error rate data; Model building module, used to build prediction models; Model training module, used to train underwater acoustic environment data and signal bit error rate data; A model output module is used to receive underwater acoustic environment data and output signal bit error rate prediction data; The communication system selection module is used to select a suitable communication system for signal transmission according to the signal bit error rate prediction data.

9. The device according to claim 8, characterized in that The data acquisition module includes a signal transceiver, and the signal transceiver specifically includes: A signal transmitting end, used for transmitting a communication signal to a signal receiving end; The underwater acoustic environment measuring device is placed at the signal transmitting end and is used to detect the underwater acoustic environment and obtain the underwater acoustic environment data; The signal receiving end is used to receive the communication signal transmitted by the signal transmitting end, perform bit error rate detection, and obtain bit error rate data.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images