Method for qualitatively evaluating waterborne sound signals transmitted via a radio link

Abstract

The invention relates to a method for qualitatively evaluating waterborne sound signals (24) transmitted via a radio link (26), comprising the following steps: a) receiving the waterborne sound signals (24); b) evaluating the received waterborne sound signals (24) on the basis of quality features of the received waterborne sound signals (24) by means of a model trained using machine learning methods; c) outputting a recommendation regarding the signal quality on the basis of the evaluation at least if the signal quality is lower than a desired signal quality.

Description

[0001] Method for the qualitative evaluation of underwater sound signals transmitted via a radio link

[0002] Description

[0003] The invention relates to the transmission of underwater sound signals via radio links.

[0004] Interference can occur during the transmission of underwater sound signals over radio links, rendering the signals unusable or even causing the signals themselves to be unusable. If a situational awareness picture is created based on a large number of underwater sound signals, for example, by beamforming with various underwater sound signals, the situational awareness picture can be distorted by faulty underwater sound signals.

[0005] Particularly in a sonar buoy processing system, the quality of the received acoustic sonar buoy signals can vary considerably, as sonar buoys are disposable items used for only a few days, often even just a few hours. Consequently, sonar buoys are manufactured inexpensively, which negatively impacts the quality of the components used. However, the presented method is not limited to sonar buoys but can be applied to any radio link that transmits underwater acoustic signals.

[0006] The quality of the received signals depends primarily on the radio link between the transmitter (e.g., sonar buoy) and the receiver, which can be affected by interference. The underwater transducer(s) in the transmitter can also be defective or malfunctioning. For the user, assessing the signal quality is usually difficult or even impossible, especially considering that standardized displays are typically used, particularly for better interpretation of the acoustics. Feedback on the quality of the received signal is only provided to the user based on the phase relationships of the carrier signals contained in the radio signal. However, this is only possible for directional sonar buoys, so-called DIFAR buoys.

[0007] The object of the present invention is therefore to create an improved concept for the quality analysis of underwater sound signals transmitted by radio link.

[0008] The problem is solved by the subject matter of the independent patent claims. Further advantageous embodiments are the subject matter of the dependent patent claims.

[0009] Exemplary embodiments show a method for the qualitative evaluation of underwater sound signals transmitted via a radio link. The method comprises the following steps a) to c). In step a), the underwater sound signals are received by a receiver. The receiver can be located on a base platform, for example, a manned or unmanned surface craft, e.g., a ship or an aircraft.

[0010] In step b), the received underwater sound signals are evaluated based on their quality characteristics using a model trained with machine learning methods. Such a model can also be referred to as artificial intelligence. Suitable training data includes real sensor data acquired during training runs, training maneuvers, or in operation. Preferably, the data is pre-classified, for example, by a trained (sonar) operator. This establishes the actual signal quality for the training data. This enables supervised learning of the model. Furthermore, synthetic data, i.e., data generated using technical means, is suitable for training the model. Synthetic data can be used, in particular, when the amount of real training data is insufficient. Preferably, a combination of real and synthetic data can be used for training in this case.

[0011] The model can optionally comprise multiple, and in particular, different, sub-models. A (sub-)model describes a trained algorithm. Most common, well-known algorithms are suitable, especially artificial neural networks, Bayesian classifiers, support vector machines (SVMs), linear regression, etc. If the model comprises several sub-models for creating the clarified situational picture, similar algorithms (e.g., different artificial neural networks) as well as different algorithms (e.g., an artificial neural network and a linear regression) can be combined. In particular, it has been found that no special algorithms need to be used to create the model. It is sufficient to train commercially available algorithms with appropriate data. Such algorithms are also referred to as COTS (Components Off-The-Shelf).It has turned out that the structure, for example the number of neurons or the number of layers in artificial neural networks, is irrelevant for creating the model. In this case, it may even be sufficient to use a simple threshold value to decide whether the signal quality is too poor.

[0012] Preferably, at least one (partial) model is implemented as an artificial neural network. The artificial neural network can be based on Transformer technology and / or be or include a convolutional artificial neural network.

[0013] In both cases, the quality of the underwater sound signals is checked. In particular, statistical measures of the received underwater sound signals can be checked as quality characteristics to determine the quality of the underwater sound signals.

[0014] The model can be based on an algorithm using any classification method. For example, a Bayesian classifier, an artificial neural network, etc., can be used. The model can be trained on the quality characteristics. That is, the underwater sound signals are analyzed to determine the quality characteristics.

[0015] In step c), a recommendation regarding signal quality is issued based on the evaluation, at least when a desired signal quality is not met. This means, for example, that a recommendation for action is given if the signal quality falls below a desired level, i.e., if the underwater acoustic signals are disrupted or not transmitted at all. If the signal quality is good, no recommendation is issued, as no action is required. However, it is also possible to indicate good signal quality, for example, with a traffic light indicator.

[0016] The idea is to analyze underwater acoustic signals received via radio link and provide an operator with a recommendation for action, at least when the signal quality of the underwater acoustic signals is insufficient. For the analysis of the underwater acoustic signals, the physical differences between disturbed, undisturbed, and absent underwater acoustic signals after transmission via radio link were investigated. It was found that the acoustic underwater acoustic signals change on a different timescale than radio signals. Furthermore, recurring patterns were observed due to echoes, i.e., reflected underwater acoustic signals. In contrast, radio interference is characterized by higher signal energy and rapid changes.

[0017] Based on these physical differences, the number of pulsatile changes in the received underwater sound signal is used as a quality criterion in exemplary implementations. Exceeding a threshold of pulsatile changes can indicate the presence of a malfunction. Additionally or alternatively, the result of comparative hypothesis tests can be used as a quality criterion. Static tests such as the Durbin-Watson test are suitable as comparative hypothesis tests.

[0018] In exemplary embodiments, in step a) underwater sound signals from a first underwater sound transducer arrangement and a second underwater sound transducer arrangement are received. Each underwater sound transducer arrangement has one or more underwater sound transducers. As a quality criterion, a correlation of the underwater sound signals from the first underwater sound transducer arrangement with the underwater sound signals from the second underwater sound transducer arrangement can be used. In particular, the underwater sound signals generated at the same time are used for the correlation. Optionally, the underwater sound signals are time-shifted depending on the distance between the underwater sound transducer arrangements. This allows the different detection times of the same event due to the different positions to be taken into account. The maximum shift can preferably correspond to the maximum sound travel time between the underwater sound transducer arrangements.

[0019] Alternatively, in step a), underwater acoustic signals from a first underwater acoustic transducer of a first underwater acoustic transducer arrangement and from a second underwater acoustic transducer of the first underwater acoustic transducer arrangement can be received. A correlation between the underwater acoustic signal of the first underwater acoustic transducer and that of the second underwater acoustic transducer can be used as a quality criterion. In principle, this embodiment corresponds to the previous embodiment. However, in this case, the underwater acoustic signals from underwater acoustic transducers arranged in the same underwater acoustic transducer arrangement are correlated. The underwater acoustic transducers in an underwater acoustic transducer arrangement are not usually spatially separated to such an extent that a time shift of the underwater acoustic signals is necessary. The correlation will also yield a high value even with small time shifts, provided the underwater acoustic signals are undisturbed.

[0020] In exemplary embodiments, step c) recommends changing the radio channel if the evaluation detects a poor radio channel. Additionally or alternatively, step c) recommends excluding the underwater sound signals from an underwater sound transducer array from further processing if the evaluation detects that the array is defective. Otherwise, the underwater sound signals could distort the overall result (e.g., a situational image) generated from a multitude of underwater sound signals from different underwater sound transducer arrays. Similarly, a computer program is disclosed comprising instructions that, when executed by a computer, cause the computer to perform the steps of the method based on underwater sound signals.

[0021] Furthermore, a receiving arrangement for receiving underwater sound signals via a radio link is disclosed. The receiving arrangement comprises a radio receiver for receiving the underwater sound signals via the radio link and a data processing unit. The data processing unit can execute the process steps based on the received underwater sound signals.

[0022] Furthermore, a multistatic sonar system is disclosed, comprising the receiving arrangement and a plurality of sonar buoys for generating the underwater sound signals, wherein the sonar buoys are configured to transmit the underwater sound signals to the radio receiver of the receiving arrangement.

[0023] Preferred embodiments of the present invention are explained below with reference to the accompanying drawing. It shows:

[0024] Fig. 1 : a schematic block diagram of a multistatic sonar system.

[0025] Before exemplary embodiments of the present invention are explained in detail below with reference to the drawings, it should be noted that identical, functionally equivalent or equivalent elements, objects and / or structures in the different figures are provided with the same reference numerals, so that the description of these elements shown in different exemplary embodiments is interchangeable or can be applied to one another.

[0026] Fig. 1 shows a schematic block diagram of a multistatic sonar system 20. The multistatic sonar system 20 comprises a receiving arrangement 22 for receiving underwater sound signals 24, 24a, 24b, 24c via a radio link 26. The receiving arrangement 22 includes a radio receiver 28, for example an antenna, and a data processing unit 30. Furthermore, the multistatic sonar system 20 comprises a plurality of sonar buoys 32 for generating the underwater sound signals 24 and for converting the underwater sound signals 24 into corresponding radio signals 34, 34a, 34b, 34c in order to transmit the underwater sound signals 24 to the receiving arrangement 22. The sonar buoys 32 can convert underwater sound 36 into the underwater sound signal by means of underwater sound transducer arrangements 38, 38a, 38b, 38c with one or more underwater sound transducers.A multistatic sonar detection method can be carried out using the buoys 32, for example by one of the buoys, the receiving arrangement, or a third party transmitting a sonar signal that is received by the sonar buoys 32 with the underwater sound transmitter 36. The detection of the sonar signal can be carried out by the data processing unit 30.

[0027] The disclosed (underwater) sound transducers are designed for use underwater, particularly in the sea. The transducers can convert underwater sound into an electrical signal (e.g., voltage or current) corresponding to the sound pressure, the (received) underwater sound signal. Furthermore, it is possible for the transducers to convert an applied electrical voltage into underwater sound. The electrical voltage can follow a predefined pattern and then be referred to as the (transmitted) sonar signal, while the underwater sound resulting from the sonar signal to be transmitted is referred to as the (transmitted) sonar signal. Examples of sonar signals are a chirp (frequency-modulated signal) or, as a special case of the chirp, a sweep (linearly frequency-modulated signal). The transducers can therefore be used as underwater sound receivers and / or underwater sound transmitters.The transducers can be made of a piezoelectric material, such as a piezoceramic, to serve as the sensor material. A plurality of underwater transducers, or one or more underwater transducers in conjunction with a signal processing unit, can be referred to as a sonar system. The transducers can be used for (active and / or passive) sonar (sound navigation and ranging). The transducers are preferably not suitable for, or are not used for, medical applications. Likewise, the transducers are preferably not used for, or are not suitable for, the ultrasonic testing of materials.Although some aspects have been described in connection with a device, it is understood that these aspects also constitute a description of the corresponding process, so that a block or component of a device is also to be understood as a corresponding process step or as a feature of a process step. Similarly, aspects described in connection with or as a process step also constitute a description of a corresponding block, detail, or feature of a corresponding device.

[0028] Depending on the implementation requirements, embodiments of the invention can be implemented in hardware or in software. The implementation can be carried out using a digital storage medium, for example, a magnetic or optical storage medium, on which electronically readable control signals, e.g., a computer program, are stored. These signals can interact with a programmable computer system (CPU and / or GPU) in such a way that the respective method is carried out. For this reason, the digital storage medium should be computer-readable. Embodiments can therefore include a data carrier that has electronically readable control signals capable of interacting with a programmable computer system in such a way that one of the methods described herein is carried out.

[0029] In some embodiments, a programmable logic device (for example, a field-programmable gate array, an FPGA) can be used to perform some or all of the functionalities of the methods described herein. In some embodiments, a field-programmable gate array can interact with a microprocessor to perform one of the methods described herein. Generally, in some embodiments, the methods are performed by any hardware device. This can be general-purpose hardware such as a computer processor (CPU) or a graphics processing unit (GPU), or hardware specific to the method, such as an ASIC. A distributed implementation on both CPU and GPU is also possible. The embodiments described above merely illustrate the principles of the present invention.It is understood that modifications and variations of the arrangements and details described herein will be obvious to other experts. Therefore, it is intended that the invention be limited only by the scope of protection of the following patent claims and not by the specific details presented herein by way of description and explanation of the exemplary embodiments.

[0030] Reference symbol list:

[0031] 20 sonar systems

[0032] 22 Receiving arrangement 24 Underwater sound signals

[0033] 26 radio link

[0034] 28 radio receivers

[0035] 30 Data processing unit

[0036] 32 sonar buoys, 34 radio signals

[0037] 36 Water sound

[0038] 38 Water transducer arrangement

Claims

Patent claims 1. Method for the qualitative evaluation of underwater sound signals (24) transmitted via a radio link (26) comprising the following steps: a) Receiving the underwater sound signals (24); b) Evaluating the received underwater sound signals (24) based on quality characteristics of the received underwater sound signals (24) using a model trained with machine learning methods; c) Outputting a recommendation regarding the signal quality based on the evaluation, at least when a desired signal quality is not met.

2. Method according to claim 1, wherein the number of pulsed changes of the received underwater sound signal (24) is used as a quality characteristic.

3. Method according to one of the preceding claims, wherein the result of comparative hypothesis tests is used as a quality characteristic.

4. Method according to one of the preceding claims, - wherein in step a) underwater sound signals (24) are received from a first underwater sound transducer arrangement (38) and a second underwater sound transducer arrangement (38); - where a correlation of the underwater sound signals (24) of the first underwater sound transducer arrangement (38) with the underwater sound signals (24) of the second underwater sound transducer arrangement (38) is used as a quality characteristic.

5. Method according to any one of claims 1 to 3, - wherein in step a) underwater sound signals (24) of a first underwater sound transducer of a first underwater sound transducer arrangement (38) and of a second underwater sound transducer of the first underwater sound transducer arrangement (38) are received; - where a correlation of the underwater sound signal (24) of the first underwater sound transducer with the second underwater sound transducer is used as a quality characteristic.

6. Method according to one of the preceding claims, wherein in step c) the recommendation to change the radio channel is issued if a poor radio channel is detected based on the evaluation.

7. Method according to one of the preceding claims, wherein in step c) a recommendation is issued to exclude the underwater sound signals (24) of an underwater sound transducer arrangement (38) from further processing if, based on the evaluation, it is detected that the underwater sound transducer arrangement (38) is defective.

8. Computer program comprising instructions which, when the program is executed by a computer, cause it to perform the steps of the method according to one of the preceding claims based on underwater sound signals (24).

9. Receiving arrangement (22) for receiving underwater sound signals (24) via a radio link with the following features: - a radio receiver (28) designed to receive the underwater sound signals (24) via the radio link; - a data processing unit (30) configured to perform the steps of the method according to any one of claims 1 to 7 based on the received underwater sound signals (24).

10. Multistatic sonar system (20) comprising the receiving arrangement (22) according to claim 9 and a plurality of sonar buoys (32) for generating the underwater sound signals (24), wherein the sonar buoys are configured to transmit the underwater sound signals (24) to the radio receiver (28) of the receiving arrangement (22).

Images