WO2022057305A1

WO2022057305A1 - Signal processing method and apparatus, terminal device and storage medium

Info

Publication number: WO2022057305A1
Application number: PCT/CN2021/096090
Authority: WO
Inventors: 何展翔; 陈晓非; 韩鹏
Original assignee: 南方科技大学; 南方海洋科学与工程广东省实验室(广州)
Priority date: 2020-09-16
Filing date: 2021-05-26
Publication date: 2022-03-24
Also published as: CN112198556A

Abstract

The present application is applicable to the technical field of signal processing, and provides a signal processing method and apparatus, a terminal device and a storage medium. The signal processing method comprises: performing signal feature extraction on a submarine electromagnetic detection signal to obtain signal features of the submarine electromagnetic detection signal; and performing, according to the signal features, denoising processing on the submarine electromagnetic detection signal by using a preset signal denoising network, to obtain a denoised submarine electromagnetic detection signal, the signal denoising network being trained by using submarine electromagnetic signal noise samples. Thus, noise and electromagnetic signals in the submarine electromagnetic detection signal can be identified according to the signal features learned by the signal denoising network, and the noise can be removed from the submarine electromagnetic detection signal, so as to specifically perform noise identification and denoising on submarine electromagnetic detection signals in a complex marine environment, thereby optimizing the denoising effect of the submarine electromagnetic detection signals, and effectively improving the quality of the submarine electromagnetic detection signals.

Description

信号处理方法、装置、终端设备及存储介质Signal processing method, device, terminal device and storage medium

本申请要求于2020年9月16日在中国专利局提交的、申请号为202010975271.4的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of the Chinese Patent Application No. 202010975271.4 filed with the Chinese Patent Office on September 16, 2020, the entire contents of which are incorporated herein by reference.

技术领域technical field

本申请属于信号处理技术领域，尤其涉及信号处理方法、装置、终端设备及存储介质。The present application belongs to the technical field of signal processing, and in particular, relates to a signal processing method, apparatus, terminal device and storage medium.

背景技术Background technique

海底电磁探测技术是采集和分析海底电磁信号进行海底电性结构探测的技术，其在海底油气资源的探测过程中起关键作用。由于海底洋流运动切割地磁场产生的感应电磁场、海洋鱼类活动和舰艇活动等因素会产生海洋电磁噪声，而海洋电磁噪声叠加在地下异常体产生的有效电磁信号之上，大大降低电磁勘探采集数据的信噪比，所以需要抑制海洋噪声，提高海底电磁信号的信噪比。The submarine electromagnetic detection technology is a technology that collects and analyzes submarine electromagnetic signals to detect the electrical structure of the submarine, which plays a key role in the detection of submarine oil and gas resources. Due to the induced electromagnetic field generated by the motion of the ocean current cutting the geomagnetic field, marine fish activities and ship activities, marine electromagnetic noise will be generated, and the marine electromagnetic noise is superimposed on the effective electromagnetic signal generated by the underground abnormal body, which greatly reduces the data collected by electromagnetic exploration. Therefore, it is necessary to suppress ocean noise and improve the signal-to-noise ratio of submarine electromagnetic signals.

在现有相关技术中，采用与陆地电磁信号相同的去噪方式对海底电磁信号进行去噪，如采用小波变换、希尔伯特黄变换或广义S变换等方式实现信号去噪。但是海底环境不同于陆地环境，海底噪声源与陆地噪声源不同，以及海水对太阳风、电离层等信号有一定的屏蔽作用，所以探测得到的海底电磁信号与陆地电磁信号的信号特征差异较大，因此采用陆地电磁信号的去噪方式对海底电磁信号进行去噪所得到的去噪结果的参考性不强。可见目前没有有效的针对海底电磁信号进行去噪的方法，使得海底电磁信号的去噪效果较差，资料信噪比难以提高，勘探效果也大打折扣。In the prior art, the same denoising method as the terrestrial electromagnetic signal is used to denoise the submarine electromagnetic signal, for example, wavelet transform, Hilbert-Huang transform or generalized S transform is used to realize signal denoising. However, the seabed environment is different from the terrestrial environment, the seabed noise source is different from the land noise source, and the seawater has a certain shielding effect on the solar wind, ionosphere and other signals, so the signal characteristics of the detected seabed electromagnetic signals and land electromagnetic signals are quite different. Therefore, the denoising result obtained by denoising the submarine electromagnetic signal by the denoising method of the terrestrial electromagnetic signal is not very useful. It can be seen that there is currently no effective method for denoising the submarine electromagnetic signal, which makes the denoising effect of the submarine electromagnetic signal poor, the data signal-to-noise ratio is difficult to improve, and the exploration effect is greatly reduced.

技术问题technical problem

本申请实施例提供了信号处理方法、装置、终端设备及存储介质，可以解决当前海底电磁信号的去噪方法中存在去噪效果差的问题。The embodiments of the present application provide a signal processing method, an apparatus, a terminal device, and a storage medium, which can solve the problem of poor denoising effect in the current denoising method for submarine electromagnetic signals.

技术解决方案technical solutions

第一方面，本申请实施例提供了一种信号处理方法，包括：In a first aspect, an embodiment of the present application provides a signal processing method, including:

对海底电磁探测信号进行信号特征提取，得到海底电磁探测信号的信号特征；Extracting the signal features of the submarine electromagnetic detection signal to obtain the signal characteristics of the submarine electromagnetic detection signal;

利用预设的信号去噪网络根据信号特征对海底电磁探测信号进行去噪处理，得到去噪后的海底电磁探测信号，信号去噪网络利用海底电磁信噪样本进行训练得到。Using a preset signal de-noising network to de-noise the submarine electromagnetic detection signal according to the signal characteristics, to obtain the de-noised submarine electromagnetic detection signal, and the signal de-noising network is obtained by training the submarine electromagnetic signal-noise samples.

本实施例提供的信号处理方法，通过对海底电磁探测信号进行信号特征提取，得到海底电磁探测信号的信号特征，从而能够分析出海底电磁探测信号的噪声特征和电磁信号特征，以有针对性地识别海底电磁探测信号中噪声和电磁信号；以及通过信号去噪网络学习复杂海洋环境中的海底电磁探测信号的信号特征，再利用信号去噪网络根据实际探测得到海底电磁探测信号的信号特征，对海底电磁探测信号进行去噪，得到去噪后的海底电磁探测信号，从而能够根据信号去噪网络所学习到的信号特征识别海底电磁探测信号的噪声和电磁信号，并将噪声从海底电磁探测信号中去除，以有针对性地对复杂海洋环境中的海底电磁探测信号进行噪声识别和去噪，进而优化海底电磁探测信号的去噪效果，有效提高海底电磁探测信号的品质。The signal processing method provided in this embodiment obtains the signal characteristics of the submarine electromagnetic detection signal by extracting the signal characteristics of the submarine electromagnetic detection signal, so that the noise characteristics and electromagnetic signal characteristics of the submarine electromagnetic detection signal can be analyzed, and the characteristics of the submarine electromagnetic detection signal can be analyzed in a targeted manner. Identify the noise and electromagnetic signals in the submarine electromagnetic detection signal; and learn the signal characteristics of the submarine electromagnetic detection signal in the complex marine environment through the signal denoising network, and then use the signal denoising network to obtain the signal characteristics of the submarine electromagnetic detection signal according to the actual detection. The submarine electromagnetic detection signal is denoised, and the denoised submarine electromagnetic detection signal is obtained, so that the noise and electromagnetic signal of the submarine electromagnetic detection signal can be identified according to the signal characteristics learned by the signal denoising network, and the noise can be removed from the submarine electromagnetic detection signal. In order to target the noise identification and denoising of the submarine electromagnetic detection signal in the complex marine environment, the denoising effect of the submarine electromagnetic detection signal is optimized, and the quality of the submarine electromagnetic detection signal is effectively improved.

第二方面，本申请实施例提供了一种信号处理装置，包括：In a second aspect, an embodiment of the present application provides a signal processing apparatus, including:

提取模块，用于对海底电磁探测信号进行信号特征提取，得到海底电磁探测信号的信号特征；The extraction module is used to extract the signal features of the submarine electromagnetic detection signal to obtain the signal characteristics of the submarine electromagnetic detection signal;

去噪模块，用于利用预设的信号去噪网络根据信号特征对海底电磁探测信号进行去噪处理，得到去噪后的海底电磁探测信号，信号去噪网络利用海底电磁信噪样本进行训练得到。The de-noising module is used to de-noise the submarine electromagnetic detection signal according to the signal characteristics by using the preset signal de-noising network to obtain the de-noised submarine electromagnetic detection signal. The signal de-noising network is obtained by training the submarine electromagnetic signal-noise samples. .

第三方面，本申请实施例提供了一种终端设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如上述第一方面中任一项所述的信号处理方法。In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, when the processor executes the computer program The signal processing method according to any one of the above first aspects is implemented.

第四方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现如上述第一方面中任一项所述的信号处理方法。In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any one of the above-mentioned first aspects is implemented. The signal processing method described above.

第五方面，本申请实施例提供了一种计算机程序产品，当计算机程序产品在终端设备上运行时，使得终端设备执行上述第一方面中任一项所述的信号处理方法。In a fifth aspect, an embodiment of the present application provides a computer program product that, when the computer program product runs on a terminal device, enables the terminal device to execute the signal processing method described in any one of the first aspects above.

可以理解的是，上述第二方面至第五方面的有益效果可以参见上述第一方面中的相关描述，在此不再赘述。It can be understood that, for the beneficial effects of the second aspect to the fifth aspect, reference may be made to the relevant description in the first aspect, which is not repeated here.

附图说明Description of drawings

为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only for the present application. In some embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

图1是本申请一实施例提供的信号处理方法的流程性示意图；1 is a schematic flowchart of a signal processing method provided by an embodiment of the present application;

图2是本申请一实施例提供的信号处理方法中步骤S101的流程性示意图；FIG. 2 is a schematic flowchart of step S101 in the signal processing method provided by an embodiment of the present application;

图3是本申请另一实施例提供的信号处理方法的流程性示意图；3 is a schematic flowchart of a signal processing method provided by another embodiment of the present application;

图4是本申请实施例提供的海底电磁信号的处理装置的结构示意图；4 is a schematic structural diagram of an apparatus for processing submarine electromagnetic signals provided by an embodiment of the present application;

图5是本申请实施例提供的终端设备的结构示意图。FIG. 5 is a schematic structural diagram of a terminal device provided by an embodiment of the present application.

本发明的实施方式Embodiments of the present invention

以下描述中，为了说明而不是为了限定，提出了诸如特定***结构、技术之类的具体细节，以便透彻理解本申请实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中，省略对众所周知的***、装置、电路以及方法的详细说明，以免不必要的细节妨碍本申请的描述。In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

应当理解，当在本申请说明书和所附权利要求书中使用时，术语“包括”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。It is to be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described feature, integer, step, operation, element and/or component, but does not exclude one or more other The presence or addition of features, integers, steps, operations, elements, components and/or sets thereof.

还应当理解，在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。It will also be understood that, as used in this specification and the appended claims, the term "and/or" refers to and including any and all possible combinations of one or more of the associated listed items.

如在本申请说明书和所附权利要求书中所使用的那样，术语“如果”可以依据上下文被解释为“当...时”或“一旦”或“响应于确定”或“响应于检测到”。类似地，短语“如果确定”或“如果检测到[所描述条件或事件]”可以依据上下文被解释为意指“一旦确定”或“响应于确定”或“一旦检测到[所描述条件或事件]”或“响应于检测到[所描述条件或事件]”。As used in the specification of this application and the appended claims, the term "if" may be contextually interpreted as "when" or "once" or "in response to determining" or "in response to detecting ". Similarly, the phrases "if it is determined" or "if the [described condition or event] is detected" may be interpreted, depending on the context, to mean "once it is determined" or "in response to the determination" or "once the [described condition or event] is detected. ]" or "in response to detection of the [described condition or event]".

另外，在本申请说明书和所附权利要求书的描述中，术语“第一”、“第二”、“第三”等仅用于区分描述，而不能理解为指示或暗示相对重要性。In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the description, and should not be construed as indicating or implying relative importance.

在本申请说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。由此，在本说明书中的不同之处出现的语句“在一个实施例中”、“在一些实施例中”、“在其他一些实施例中”、“在另外一些实施例中”等不是必然都参考相同的实施例，而是意味着“一个或多个但不是所有的实施例”，除非是以其他方式另外特别强调。术语“包括”、“包含”、“具有”及它们的变形都意味着“包括但不限于”，除非是以其他方式另外特别强调。References in this specification to "one embodiment" or "some embodiments" and the like mean that a particular feature, structure or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in other embodiments," etc. in various places in this specification are not necessarily All refer to the same embodiment, but mean "one or more but not all embodiments" unless specifically emphasized otherwise. The terms "including", "including", "having" and their variants mean "including but not limited to" unless specifically emphasized otherwise.

如背景技术相关记载，采用与陆地电磁信号相同的去噪方式对海底电磁信号进行去噪，如采用小波变换、希尔伯特黄变换或广义S变换等方式实现信号去噪。但是海底环境不同于陆地环境，海底噪声源与陆地噪声源不同，以及海水对信号有一定的屏蔽作用，所以探测得到的海底电磁信号与陆地电磁信号的信号特征差异较大，因此采用陆地电磁信号的去噪方式对海底电磁信号进行去噪所得到的去噪结果的参考性不强。可见目前无法有效针对海底电磁信号进行去噪，使得海底电磁信号的去噪效果较差。As described in the background art, the submarine electromagnetic signal is de-noised by the same de-noising method as the terrestrial electromagnetic signal, such as wavelet transform, Hilbert-Huang transform or generalized S transform, etc. to achieve signal de-noising. However, the seabed environment is different from the terrestrial environment. The seabed noise source is different from the land noise source, and the seawater has a certain shielding effect on the signal, so the signal characteristics of the detected seabed electromagnetic signal and the terrestrial electromagnetic signal are quite different, so the terrestrial electromagnetic signal is used. The denoising method obtained by denoising the submarine electromagnetic signal is not very referential. It can be seen that it is impossible to effectively denoise the submarine electromagnetic signal at present, which makes the denoising effect of the submarine electromagnetic signal poor.

有鉴于此，本申请实施例提供一种信号处理方法，通过对海底电磁探测信号进行信号特征提取，得到海底电磁探测信号的信号特征，从而能够分析出海底电磁探测信号的噪声特征和电磁信号特征，以有针对性地识别海底电磁探测信号中噪声和电磁信号；以及通过信号去噪网络学习复杂海洋环境中的海底电磁探测信号的信号特征，再利用信号去噪网络根据实际探测得到海底电磁探测信号的信号特征，对海底电磁探测信号进行去噪，得到去噪后的海底电磁探测信号，从而能够根据信号去噪网络所学习到的信号特征识别海底电磁探测信号的噪声和电磁信号，并将噪声从海底电磁探测信号中去除，以有针对性地对复杂海洋环境中的海底电磁探测信号进行噪声识别和去噪，进而优化海底电磁探测信号的去噪效果，有效提高海底电磁探测信号的去噪质量。In view of this, the embodiment of the present application provides a signal processing method, by performing signal feature extraction on the submarine electromagnetic detection signal to obtain the signal characteristics of the submarine electromagnetic detection signal, so that the noise characteristics and electromagnetic signal characteristics of the submarine electromagnetic detection signal can be analyzed. , in order to identify the noise and electromagnetic signals in the submarine electromagnetic detection signal in a targeted manner; and learn the signal characteristics of the submarine electromagnetic detection signal in the complex marine environment through the signal de-noising network, and then use the signal de-noising network to obtain the submarine electromagnetic detection signal according to the actual detection. The signal characteristics of the signal, denoising the submarine electromagnetic detection signal, and obtain the denoised submarine electromagnetic detection signal, so that the noise and electromagnetic signal of the submarine electromagnetic detection signal can be identified according to the signal characteristics learned by the signal denoising network, and the Noise is removed from the submarine electromagnetic detection signal, so as to identify and de-noise the submarine electromagnetic detection signal in a complex marine environment in a targeted manner, thereby optimizing the denoising effect of the submarine electromagnetic detection signal, and effectively improving the denoising effect of the submarine electromagnetic detection signal. noise quality.

请参阅图1，图1示出了本申请一实施例提供的一种信号处理方法的示意性流程图。本申请提供的信号处理方法的执行主体为终端设备，终端设备包括但不限于智能手机、笔记本电脑、平板电脑、超级计算机、个人数字助理等移动终端，也可以包括台式电脑、服务器等终端设备。如图1所示的信号处理方法包括S101至S102，详述如下。Please refer to FIG. 1. FIG. 1 shows a schematic flowchart of a signal processing method provided by an embodiment of the present application. The execution subject of the signal processing method provided by this application is a terminal device, and the terminal device includes but is not limited to mobile terminals such as smart phones, notebook computers, tablet computers, supercomputers, personal digital assistants, etc., and may also include terminal devices such as desktop computers and servers. The signal processing method shown in FIG. 1 includes S101 to S102, which are described in detail as follows.

S101，对海底电磁探测信号进行信号特征提取，得到海底电磁探测信号的信号特征。S101 , extracting signal features of the submarine electromagnetic detection signal to obtain signal characteristics of the submarine electromagnetic detection signal.

在本实施例中，终端设备预先获取海底电磁探测信号。海底电磁探测信号为海底电磁采集站在海底实际探测得到的海底电磁信号，该海底电磁探测信号中包含海底电磁信号和海底噪声信号。其中，海底电磁信号为海底大地的电磁信号，其主要信号来源包括电离层、磁暴和地磁脉动；海底噪声信号为海洋环境或人文活动产生的噪声，例如，海底洋流切割地球磁场产生的电磁噪声，舰艇活动产生的电磁信号，船舰上的用电设备产生的电磁信号。In this embodiment, the terminal device obtains the submarine electromagnetic detection signal in advance. The submarine electromagnetic detection signal is the submarine electromagnetic signal obtained by the submarine electromagnetic acquisition station actually detected by the submarine, and the submarine electromagnetic detection signal includes the submarine electromagnetic signal and the submarine noise signal. Among them, the submarine electromagnetic signal is the electromagnetic signal of the seabed earth, and its main signal sources include the ionosphere, magnetic storm and geomagnetic pulsation; the submarine noise signal is the noise generated by the marine environment or human activities, for example, the electromagnetic noise generated by the ocean current cutting the earth's magnetic field, Electromagnetic signals generated by ship activities and electromagnetic signals generated by electrical equipment on ships.

海底电磁采集站为下潜到海底探测海底电磁探测信号的设备，该设备的结构组成包括但不限于电磁数据记录仪、电场传感器、磁场传感器、信标、释放器、方位与CTD记录仪、温度计、浮球、锚系和框架。可以理解的是，终端设备可以与海底电磁采集站通信连接，从而获取海底电磁采集站实时采集到的海底电磁探测信号，终端设备也可以与服务器通信连接，服务器与海底电磁采集站通信连接，以使海底电磁采集站采集到的海底电磁探测信号上传至服务器，终端设备再从服务器下载该海底电磁探测信号。The submarine electromagnetic acquisition station is a device that dives to the seabed to detect submarine electromagnetic detection signals. The structure of the device includes but is not limited to electromagnetic data recorders, electric field sensors, magnetic field sensors, beacons, releasers, azimuth and CTD recorders, and thermometers. , floats, moorings and frames. It can be understood that the terminal equipment can be communicated and connected with the submarine electromagnetic acquisition station, so as to obtain the submarine electromagnetic detection signal collected by the submarine electromagnetic acquisition station in real time. The submarine electromagnetic detection signal collected by the submarine electromagnetic acquisition station is uploaded to the server, and the terminal device downloads the submarine electromagnetic detection signal from the server.

终端设备对海底电磁探测信号进行信号特征提取，得到海底电磁探测信号的信号特征。信号特征包括海底电磁探测信号的波形特征、基于波形得到的梅尔频率倒谱系数和功率谱密度等。其中，波形特征为海底电磁探测信号的基本特征，其包括但不限于海底电磁探测信号的信号频率范围、幅值、瞬时频率和信号持续时长等，梅尔频率倒谱系数为对海底电磁探测信号进行频谱分析得到的物理量，通过将信号在时间域中的波形转换为频率域的频谱，即将波形进行编码得到特征向量，进而可以对信号的信息作定量分析。功率谱密度为对海底电磁探测信号进行随机振动分析得到的物理量，通过概率分布函数描述波形的连续瞬态响应。The terminal equipment performs signal feature extraction on the submarine electromagnetic detection signal to obtain the signal characteristics of the submarine electromagnetic detection signal. The signal characteristics include the waveform characteristics of the submarine electromagnetic detection signal, the Mel frequency cepstral coefficient and the power spectral density obtained based on the waveform. Among them, the waveform feature is the basic feature of the submarine electromagnetic detection signal, which includes but is not limited to the signal frequency range, amplitude, instantaneous frequency and signal duration of the submarine electromagnetic detection signal, and the Mel frequency cepstral coefficient is the signal for the submarine electromagnetic detection signal. The physical quantity obtained by spectrum analysis can be used to quantitatively analyze the information of the signal by converting the waveform of the signal in the time domain into the spectrum of the frequency domain, that is, encoding the waveform to obtain the eigenvector. The power spectral density is a physical quantity obtained by random vibration analysis of the submarine electromagnetic detection signal, and the continuous transient response of the waveform is described by the probability distribution function.

示例性地，在探测海底电磁探测信号时，通常将海底电磁采集站置于海底几天甚至几个月的时间，使海底电磁采集站采集在几天甚至几个月内的海底电磁探测信号，由于海水对信号有屏蔽作用，所以海底电磁采集站采集到的部分信号的信号强度较弱，以及海底电磁探测信号中可能包括有确定信号和随机信号。因此终端设备对海底电磁探测信号进行短时傅里叶变换，得到海底电磁探测信号的号频率范围、幅值、瞬时频率和信号持续时长等波形特征，从而得到海底电磁探测信号的基本信息；基于该波形特征，再对海底电磁探测信号进行梅尔频率倒谱分析，得到海底电磁探测信号的梅尔频率倒谱系数，从而能够针对海底电磁探测信号中确定信号进行频谱分析，以将确定信号编码为特征向量进行定量分析；基于该波形特征，还对海底电磁探测信号进行傅里叶变换，得到海底电磁探测信号的功率谱密度，从而能够针对海底电磁探测信号中的随机信号进行功率谱分析，以利用功率谱分析不随时间推移而变化的统计特性，即海底电磁探测信号的随机过程的自相关函数能够在时域完整描述其统计特性，使得功率谱密度能够在频域对随机过程统计特性进行完整描述。Exemplarily, when detecting the submarine electromagnetic detection signal, the submarine electromagnetic acquisition station is usually placed on the ocean floor for several days or even months, so that the submarine electromagnetic acquisition station collects the submarine electromagnetic detection signal within a few days or even a few months, Because the seawater has a shielding effect on the signal, the signal strength of some of the signals collected by the submarine electromagnetic acquisition station is weak, and the submarine electromagnetic detection signal may include definite signals and random signals. Therefore, the terminal equipment performs short-time Fourier transform on the submarine electromagnetic detection signal to obtain the waveform characteristics such as the frequency range, amplitude, instantaneous frequency and signal duration of the submarine electromagnetic detection signal, thereby obtaining the basic information of the submarine electromagnetic detection signal; Based on the waveform characteristics, the Mel frequency cepstrum analysis is performed on the submarine electromagnetic detection signal to obtain the Mel frequency cepstral coefficient of the submarine electromagnetic detection signal, so that the spectrum analysis can be performed on the determined signal in the submarine electromagnetic detection signal to encode the determined signal. Quantitative analysis is performed for the eigenvector; based on the waveform characteristics, Fourier transform is also performed on the submarine electromagnetic detection signal to obtain the power spectral density of the submarine electromagnetic detection signal, so that the power spectrum analysis can be performed for the random signal in the submarine electromagnetic detection signal, In order to use the statistical characteristics of the power spectrum analysis that do not change with time, that is, the autocorrelation function of the random process of the submarine electromagnetic detection signal can completely describe its statistical characteristics in the time domain, so that the power spectral density can be used in the frequency domain. full description.

S102，利用预设的信号去噪网络根据信号特征对海底电磁探测信号进行去噪处理，得到去噪后的海底电磁探测信号，信号去噪网络利用海底电磁信噪样本进行训练得到。S102, using a preset signal de-noising network to de-noise the submarine electromagnetic detection signal according to the signal characteristics, to obtain a de-noised submarine electromagnetic detection signal, and the signal de-noising network is obtained by training the submarine electromagnetic signal-noise samples.

在本实施例中，终端设备预先存储有预先训练好的信号去噪网络。该信号去噪网络是使用机器学习算法对海底电磁信噪样本进行训练得到的，海底电磁信噪样本包括海底电磁信号样本和海底噪声信号样本。可以理解的是，该信号去噪网络可以由终端设备预先训练好，也可以由其他设备预先训练好后将该信号去噪网络对应的文件移植至本终端设备中。也就是说，训练该去噪信号网络的执行主体与使用该去噪信号网络的执行主体可以是相同的，也可以是不同的。In this embodiment, the terminal device pre-stores a pre-trained signal denoising network. The signal denoising network is obtained by using machine learning algorithm to train seabed electromagnetic signal-noise samples, and the seabed electromagnetic signal-noise samples include seabed electromagnetic signal samples and seabed noise signal samples. It can be understood that the signal denoising network can be pre-trained by the terminal device, or the file corresponding to the signal de-noising network can be transplanted to the terminal device after being pre-trained by other devices. That is to say, the executive body for training the denoising signal network and the executive body for using the denoising signal network may be the same or different.

示例性地，在训练信号去噪网络时，机器学习算法为深度置信网络算法，基于限玻尔兹曼机(RBM，Restricted Boltzmann Machine)对信号去噪网络进行无监督预训练，再利用前向传播算法和反向传播算法对预训练好的信号去噪网络进行有监督调优训练，直至信号去噪网络达到收敛条件。具体地，将标定好的海底电磁信噪样本输入初始信号去噪网络中进行无监督训练，以更新初始信号去噪网络的权重和偏置值，得到预训练好的信号去噪网络。再利用前向传播算法和反向传播算法对预训练好的信号去噪网络进行有监督调优训练，以更新预训练好的信号去噪网络的权重和偏置值，直至信号去噪网络达到收敛条件，得到训练好的信号去噪网络。Exemplarily, when training the signal denoising network, the machine learning algorithm is a deep belief network algorithm, and the signal denoising network is pre-trained unsupervised based on a Restricted Boltzmann Machine (RBM, Restricted Boltzmann Machine), and then the forward The propagation algorithm and the back-propagation algorithm perform supervised tuning training on the pre-trained signal denoising network until the signal denoising network reaches the convergence condition. Specifically, the calibrated submarine electromagnetic signal-noise samples are input into the initial signal denoising network for unsupervised training to update the weight and bias values of the initial signal denoising network to obtain a pre-trained signal denoising network. Then use the forward propagation algorithm and the back propagation algorithm to perform supervised tuning training on the pre-trained signal denoising network to update the weight and bias value of the pre-trained signal denoising network until the signal denoising network reaches Convergence condition, get trained signal denoising network.

海底电磁探测信号中包含海底电磁信号和海底噪声信号，所以通过信号去噪网络根据海底电磁信噪样本中的海底电磁信号样本和海底噪声信号样本，预先学习海底电磁信号的信号特征和海底噪声信号的信号特征，并根据信号特征将海底电磁信号与海底噪声信号进行分离，从而使信号去噪网络能够根据学习到的信号特征识别出海底电磁探测信号中的海底电磁信号和海底噪声信号，并将海底噪声信号从海底电磁探测信号中去除掉，得到去噪后的海底电磁探测信号。进而能够有针对性地对复杂海洋环境中的海底电磁探测信号进行噪声识别和去噪，优化海底电磁探测信号的去噪效果，有效提高海底电磁探测信号的品质。The submarine electromagnetic detection signal contains submarine electromagnetic signals and submarine noise signals, so the signal characteristics of the submarine electromagnetic signals and the submarine noise signal are learned in advance according to the submarine electromagnetic signal samples and the submarine noise signal samples in the submarine electromagnetic signal noise samples through the signal denoising network. According to the signal characteristics, the submarine electromagnetic signal and the submarine noise signal are separated according to the signal characteristics, so that the signal denoising network can identify the submarine electromagnetic signal and the submarine noise signal in the submarine electromagnetic detection signal according to the learned signal characteristics. The seabed noise signal is removed from the seabed electromagnetic detection signal, and the denoised seabed electromagnetic detection signal is obtained. Furthermore, the noise identification and denoising of the submarine electromagnetic detection signal in the complex marine environment can be carried out in a targeted manner, the denoising effect of the submarine electromagnetic detection signal can be optimized, and the quality of the submarine electromagnetic detection signal can be effectively improved.

请参阅图2，图2示出了本申请一实施例提供的信号处理方法中步骤S101的示意性流程图。相比于图1实施例，图2实施例中信号特征包括海底电磁探测信号的波形特征、梅尔频率倒谱系数和功率谱密度，本实施例提供的信号处理方法中的步骤S101具体包括步骤S201至S203。详述如下：Please refer to FIG. 2. FIG. 2 shows a schematic flowchart of step S101 in the signal processing method provided by an embodiment of the present application. Compared with the embodiment of FIG. 1 , the signal characteristics in the embodiment of FIG. 2 include the waveform characteristics, Mel frequency cepstral coefficients and power spectral density of the submarine electromagnetic detection signal. Step S101 in the signal processing method provided by this embodiment specifically includes the following steps. S201 to S203. Details are as follows:

S201，对海底电磁探测信号进行短时傅里叶变换，得到海底电磁探测信号的波形特征。S201 , performing short-time Fourier transform on the submarine electromagnetic detection signal to obtain waveform characteristics of the submarine electromagnetic detection signal.

在本实施例中，短时傅里叶变换(STFT，short-time Fourier transform，或short-term Fourier transform))是和傅里叶变换相关的一种数学变换，用以确定时域信号的局部区域正弦波的频率与相位。而海底电磁探测信号为海底电磁采集站采集到的几天甚至几个月时长的探测信号，可见该探测信号是时域信号，所以能够对海底电磁探测信号进行短时傅里叶变换，得到海底电磁探测信号在不同时间窗口下的波形特征。In this embodiment, the short-time Fourier transform (STFT, short-time Fourier transform, or short-term Fourier transform) is a mathematical transform related to the Fourier transform, and is used to determine the local area of the time-domain signal. The frequency and phase of the area sine wave. The submarine electromagnetic detection signal is the detection signal of several days or even months collected by the submarine electromagnetic acquisition station. It can be seen that the detection signal is a time domain signal, so the short-time Fourier transform of the submarine electromagnetic detection signal can be performed to obtain the submarine electromagnetic detection signal. Waveform characteristics of electromagnetic detection signals in different time windows.

可选地，短时傅里叶变换的计算公式为：Optionally, the calculation formula of the short-time Fourier transform is:

其中

用于起时限作用，

用于起频限作用，随着时间τ的不断改变，由

所确定的时窗函数在时间轴上移动，则可以得到该时窗函数移动至时间轴的各个位置时，海底电磁探测信号在该时间窗口下的频率时间特性曲线，从而可以得到每个频率时间特性曲线的瞬时频率、幅值、频率范围和信号持续时长等波形特征。 in

for time-limiting purposes,

Used to play the role of frequency limit, with the continuous change of time τ, by

When the determined time window function moves on the time axis, the frequency-time characteristic curve of the submarine electromagnetic detection signal under this time window can be obtained when the time window function moves to each position of the time axis, so that each frequency time can be obtained. Waveform characteristics such as instantaneous frequency, amplitude, frequency range and signal duration of the characteristic curve.

S202，对海底电磁探测信号进行梅尔频率倒谱分析，得到海底电磁探测信号的梅尔频率倒谱系数。S202 , performing Mel-frequency cepstral analysis on the submarine electromagnetic detection signal to obtain a Mel-frequency cepstral coefficient of the submarine electromagnetic detection signal.

在本实施例中，梅尔频率倒谱系数(Mel-Frequency Cepstral Coefficients，MFCC)是基于海底电磁频率的非线性梅尔刻度的对数能量频谱的线性变换得到的梅尔频率倒谱的系数。通过对海底电磁探测信号进行梅尔频率倒谱分析，将海底电磁探测信号采用倒谱向量描述，每个倒谱向量表示梅尔刻度下一段信号的MFCC特征向量。In this embodiment, the Mel-Frequency Cepstral Coefficients (MFCC) are the coefficients of the Mel-frequency cepstral obtained by linear transformation of the logarithmic energy spectrum of the nonlinear Mel scale of the seabed electromagnetic frequency. Through the Mel-frequency cepstrum analysis of the submarine electromagnetic detection signal, the submarine electromagnetic detection signal is described by a cepstrum vector, and each cepstrum vector represents the MFCC feature vector of the next signal on the Mel scale.

示例性地，设定海底电磁探测信号为x(t)，海底电磁信号为b(t)，海底噪声信号为g(t)，则有x(t)＝b(t)+g(t)；对x(t)进行傅里叶变换获得频域信号X(f)，对频域X(f)两边取log：log(X(f))＝log(B(f))+log(G(f))；再进行反傅里叶变换得到： IDFT(log(X(f)))＝IDFT(log(B(f)))+IDFT(log(G(f)))，简化得到的海底电磁探测信号的时域信号为：X’(t)＝b’(t)+g’(t)，最后对该时域信号进行离散余弦变换(DCT)，取DCT结果的第2个至第13个系数作为MFCC系数。Exemplarily, set the submarine electromagnetic detection signal as x(t), the submarine electromagnetic signal as b(t), and the submarine noise signal as g(t), then x(t)=b(t)+g(t) ; Perform Fourier transform on x(t) to obtain frequency domain signal X(f), and take log on both sides of frequency domain X(f): log(X(f))=log(B(f))+log(G (f)); then perform the inverse Fourier transform to obtain: IDFT(log(X(f)))=IDFT(log(B(f)))+IDFT(log(G(f))), which is obtained by simplification The time domain signal of the submarine electromagnetic detection signal is: X'(t)=b'(t)+g'(t). Finally, the discrete cosine transform (DCT) is performed on the time domain signal, and the second to The 13th coefficient is used as the MFCC coefficient.

S203，对海底电磁探测信号进行傅里叶变换，得到海底电磁探测信号的功率谱密度。S203, Fourier transform is performed on the submarine electromagnetic detection signal to obtain the power spectral density of the submarine electromagnetic detection signal.

在本实施例中，计算海底电磁探测信号的功率谱密度(PSD)，该PSD反映信号功率如何随频率分布，即信号功率谱密度值随频率变换的曲线。示例性地，海底电磁探测信号x(t)进行傅里叶变换，得到变换结果为X(f)，则功率谱密度

从而可获得在频率f处、宽度为df的频带内的信号能量。 In this embodiment, the power spectral density (PSD) of the submarine electromagnetic detection signal is calculated, and the PSD reflects how the signal power is distributed with frequency, that is, the curve of the signal power spectral density value changing with frequency. Exemplarily, Fourier transform is performed on the submarine electromagnetic detection signal x(t), and the transformation result is obtained as X(f), then the power spectral density is

The signal energy in a frequency band of width df at frequency f can thus be obtained.

请参阅图3，图3示出了本申请另一实施例提供的信号处理方法的示意性流程图。相比于图1实施例，本实施例提供的信号处理方法在步骤S102之前还包括步骤S301至S303。详述如下：Referring to FIG. 3 , FIG. 3 shows a schematic flowchart of a signal processing method provided by another embodiment of the present application. Compared with the embodiment in FIG. 1 , the signal processing method provided by this embodiment further includes steps S301 to S303 before step S102 . Details are as follows:

S301，获取海底电磁信噪样本，海底电磁信噪样本包括信号样本和噪声样本。S301 , acquiring a submarine electromagnetic signal-noise sample, where the submarine electromagnetic signal-noise sample includes a signal sample and a noise sample.

在本实施例中，终端设备获取信号样本和噪声样本，信号样本为海底电磁采集站在海底采集到的电磁信号样本，该信号样本包括多种目标天气时的海底电磁实测信号；噪声样本为模拟海洋洋流运动或实测舰艇运动产生的噪声样本。In this embodiment, the terminal device acquires a signal sample and a noise sample, the signal sample is an electromagnetic signal sample collected by a submarine electromagnetic acquisition station on the seabed, and the signal sample includes submarine electromagnetic measured signals in various target weathers; the noise sample is an analog signal Noise samples generated by ocean current movement or measured ship movement.

在一种可能实现的方式中，获取海底电磁信噪样本，包括：获取多种目标天气时的海底电磁实测信号，将海底电磁实测信号作为信号样本；获取多种海底洋流产生的电磁场信号，将海底噪声作为噪声样本。In a possible implementation manner, acquiring submarine electromagnetic signal-noise samples includes: acquiring submarine electromagnetic measured signals in various target weathers, and using the submarine electromagnetic measured signals as signal samples; acquiring electromagnetic field signals generated by various submarine ocean currents, Seafloor noise as a noise sample.

在本实施例中，由于海洋环境多变，在不同天气下洋流产生的噪声有所不同，所以采集多种天气下的海底电磁实测信号作为信号样本。目标天气包括但不限于太阳磁暴、台风、地震、海啸、晴天以及雨天。示例性地，获取在目标天气时的海底电磁信号，将海底电磁信号作为信号样本，包括：获取预设时间段内的海底电磁实测信号；根据目标天气的发生时间段与预设时间段进行匹配；将预设时间段内与发生时间段匹配的时间段对应的海底电磁实测信号作为信号样本。例如，海底电磁采集站采集6个月内的海底电磁实测信号，在根据天气报道海底电磁采集站所在海域发生台风等目标天气的时间段，将时间段对应在上述6个月内对应的时间段，将时间段内采集到的海底电磁实测信号，作为台风等目标天气时的信号样本。In this embodiment, due to the changeable marine environment, the noise generated by ocean currents in different weathers is different, so the measured submarine electromagnetic signals under various weathers are collected as signal samples. Target weather includes, but is not limited to, solar magnetic storms, typhoons, earthquakes, tsunamis, sunny days, and rainy days. Exemplarily, acquiring a submarine electromagnetic signal during the target weather, and using the submarine electromagnetic signal as a signal sample, includes: acquiring a submarine electromagnetic measured signal within a preset time period; matching the occurrence time period of the target weather with the preset time period ; Use the submarine electromagnetic measured signal corresponding to the time period matching the occurrence time period within the preset time period as the signal sample. For example, the submarine electromagnetic acquisition station collects the submarine electromagnetic measured signals within 6 months, and in the time period when the target weather such as typhoon occurs in the sea area where the submarine electromagnetic acquisition station is located according to the weather report, the time period corresponds to the time period corresponding to the above 6 months , and the measured submarine electromagnetic signals collected during the time period are used as signal samples during target weather such as typhoons.

可选地，获取多种海底洋流产生的电磁场信号，将海底噪声作为海底电磁噪声样本，包括：通过电磁场三维正演工具模拟多种海底洋流的洋流运动；获取每种洋流运动产生的感应电场强度和感应磁场强度；根据感应电场强度和感应磁场强度，运算得到每种海底洋流产生的电磁场信号作为海底电磁噪声样本。Optionally, acquiring electromagnetic field signals generated by a variety of seabed ocean currents, and taking the seafloor noise as a sample of seabed electromagnetic noise, including: simulating the current motion of a variety of seabed ocean currents through a three-dimensional electromagnetic field forward modeling tool; obtaining the induced electric field intensity generated by each ocean current motion and the intensity of the induced magnetic field; according to the intensity of the induced electric field and the induced magnetic field, the electromagnetic field signal generated by each seafloor current is obtained by operation as a sample of seabed electromagnetic noise.

在本实施例中，对海底洋流进行三维模拟，研究海底洋流产生的电磁噪声的特征规律，获得噪声特征的数学模型和噪声样本。示例性地，利用电磁场三维正演软件模拟洋流切割地磁场产生的电磁感应强度，主要的洋流类型有三种：一是常流：沿一定路径、方向的大规模海水运动，如陆上河流，具恒稳性，速度一般在1-5km/h；二是潮夕流：由潮汐涨落引起的海水运动，具有周期性，速度一般在3-10km/h；三是风暴流：由海面强风引起的海水运动，随季节气候而变化，具有随机性，速度一般在10-50km/h。这三种主要洋流的差别除了运动规律不同外，还有运动速度、方向和能量不同，但模拟计算的基本原理方法是相同的。因此，根据运动的海水因切割地磁场而产生感应电磁场，感应电场强度E和感应磁场强度H满足如下麦克斯韦方程：In this embodiment, a three-dimensional simulation is performed on the submarine ocean current, and the characteristic law of the electromagnetic noise generated by the submarine ocean current is studied, and a mathematical model and noise samples of the noise characteristics are obtained. Exemplarily, using the electromagnetic field three-dimensional forward modeling software to simulate the electromagnetic induction intensity generated by ocean currents cutting the geomagnetic field, there are three main types of ocean currents. Constant stability, the speed is generally 1-5km/h; the second is tidal current: seawater movement caused by tidal fluctuations, with periodicity, the speed is generally 3-10km/h; the third is storm flow: caused by strong winds on the sea surface The movement of seawater varies with the seasonal climate and is random, and the speed is generally 10-50km/h. The differences between these three main ocean currents are not only the movement laws, but also the movement speed, direction and energy, but the basic principles and methods of the simulation calculation are the same. Therefore, according to the induced electromagnetic field generated by the moving seawater due to cutting the geomagnetic field, the induced electric field strength E and the induced magnetic field strength H satisfy the following Maxwell equations:

其中，μ为海水磁导率，ε为海水的介电常数，J为电流密度。在海水中，J＝σ(E+V x B)，V为海水运动速度，B为地球磁场强度，σ为海水的电导率。H、E都是海水深度体积的函数，因此通过模拟即可计算出海底洋流产生的海底电磁场的频率特性及其幅值。具体地，包括常流、潮汐流和风暴流的持续时间长度、主要频率范围和幅值。Among them, μ is the permeability of seawater, ε is the dielectric constant of seawater, and J is the current density. In seawater, J=σ(E+V x B), V is the speed of seawater movement, B is the strength of the earth's magnetic field, and σ is the conductivity of seawater. Both H and E are functions of the depth and volume of the seawater, so the frequency characteristics and amplitudes of the submarine electromagnetic fields generated by the submarine currents can be calculated through simulation. Specifically, the duration lengths, main frequency ranges and amplitudes of normal currents, tidal currents and storm currents are included.

S302，对信号样本和噪声样本进行特征提取，得到信号样本特征和噪声样本特征。S302, perform feature extraction on the signal sample and the noise sample to obtain the signal sample feature and the noise sample feature.

在本实施例中，信号样本和噪声样本的特征提取过程类似于图1实施例对海底电磁探测信号的特征提取过程，在此不再赘述。In this embodiment, the feature extraction process of the signal samples and the noise samples is similar to the feature extraction process of the submarine electromagnetic detection signal in the embodiment of FIG. 1 , and details are not repeated here.

在一种可能实现方式中，由于信号样本包括多种目标天气时的海底电磁实测信号，噪声样本包括多种海底洋流产生的电磁场信号，因此对信号样本和噪声样本进行特征提取，得到信号样本特征和噪声样本特征，包括：提取每种目标天气时的海底电磁实测信号的第一特征，以及提取每种海底洋流产生的电磁场信号的第二特征；对每种海底电磁实测信号的第一特征进行特征拼接，得到信号样本特征；对每种电磁场信号的第二特征进行特征拼接，得到噪声样本特征。In a possible implementation manner, since the signal samples include submarine electromagnetic measured signals in various target weathers, and the noise samples include electromagnetic field signals generated by various submarine ocean currents, feature extraction is performed on the signal samples and the noise samples to obtain the characteristics of the signal samples. and noise sample features, including: extracting the first feature of the submarine electromagnetic measured signal in each target weather, and extracting the second feature of the electromagnetic field signal generated by each submarine current; Feature splicing is performed to obtain signal sample features; feature splicing is performed on the second feature of each electromagnetic field signal to obtain noise sample features.

在本实施例中，对太阳磁暴、地磁、地震、台风等目标天气的信号特征进行拼接，得到信号样本的主要特征：持续时间长度，主要频率范围，幅值，梅尔倒谱系数MFCC和功率谱密度。对洋流切割磁场产生的噪声特征、实测舰艇运动产生的噪声特征进行拼接，获得噪声样本的主要特征：持续时间长度，主要频率范围，幅值，梅尔倒谱系数MFCC和功率谱密度。In this embodiment, the signal characteristics of target weather such as solar magnetic storm, geomagnetism, earthquake, typhoon, etc. are spliced to obtain the main characteristics of the signal sample: duration, main frequency range, amplitude, Mel cepstral coefficient MFCC and power spectral density. The noise characteristics generated by the ocean current cutting magnetic field and the noise characteristics generated by the measured ship motion are spliced to obtain the main characteristics of the noise samples: duration length, main frequency range, amplitude, Mel cepstral coefficient MFCC and power spectral density.

本实施例通过对多种目标天气下的信号样本进行拼接，以得到不同天气下的海底电磁信号的信号特征，使得机器学习网络能够基于该样本特征学习不同天气下的海底电磁信号的信号特征，使得信号去噪网络能够对不同天气下采集到海底电磁探测信号均有优秀的去噪效果。通过对洋流运动和舰艇运动等产生的噪声样本进行拼接，以得到海底噪声特征，并作为噪声标定数据使得机器学习网络海底噪声的噪声特征，以更好的识别出海底噪声并将其去除。In this embodiment, the signal samples of various target weathers are spliced to obtain the signal characteristics of the submarine electromagnetic signals in different weathers, so that the machine learning network can learn the signal characteristics of the submarine electromagnetic signals in different weathers based on the sample characteristics. This enables the signal denoising network to have excellent denoising effect on the submarine electromagnetic detection signals collected in different weathers. By splicing the noise samples generated by ocean current movement and ship movement, the seafloor noise features are obtained, and as the noise calibration data, the machine learns the noise features of the seafloor noise in the network to better identify and remove the seafloor noise.

S303，利用信号样本特征和噪声样本特征对预设机器学习网络进行训练，直至预设机器学习网络达到预设收敛条件，得到信号去噪网络。S303 , using the signal sample features and the noise sample features to train a preset machine learning network until the preset machine learning network reaches a preset convergence condition, and a signal denoising network is obtained.

在本实施例中，预设机器学习网络可以为深度置信网络、卷积神经网络等网络模型。当预设机器学习网络为深度置信网络时，基于限玻尔兹曼机(RBM，Restricted Boltzmann Machine)对信号去噪网络进行无监督预训练，再利用前向传播算法和反向传播算法对预训练好的信号去噪网络进行有监督调优训练，直至信号去噪网络达到预设收敛条件。可以理解的是，对于深度置信网络，预设收敛条件为学习率λ小于预设阈值，也可以为有监督调优训练的迭代次数达到预设值。In this embodiment, the preset machine learning network may be a network model such as a deep belief network and a convolutional neural network. When the preset machine learning network is a deep belief network, unsupervised pre-training is performed on the signal denoising network based on Restricted Boltzmann Machine (RBM, Restricted Boltzmann Machine). The trained signal denoising network undergoes supervised tuning training until the signal denoising network reaches the preset convergence condition. It can be understood that, for the deep belief network, the preset convergence condition is that the learning rate λ is less than the preset threshold, or the number of iterations of the supervised tuning training can reach the preset value.

应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

对应于上文实施例的信号处理方法，图4示出了本申请实施例提供的海底电磁信号的处理装置的结构框图，为了便于说明，仅示出了与本申请实施例相关的部分。Corresponding to the signal processing methods of the above embodiments, FIG. 4 shows a structural block diagram of the apparatus for processing submarine electromagnetic signals provided by the embodiments of the present application. For convenience of description, only the parts related to the embodiments of the present application are shown.

参照图4，该装置包括：Referring to Figure 4, the device includes:

提取模块401，用于对海底电磁探测信号进行信号特征提取，得到海底电磁探测信号的信号特征；The extraction module 401 is configured to perform signal feature extraction on the submarine electromagnetic detection signal to obtain the signal characteristics of the submarine electromagnetic detection signal;

去噪模块402，用于利用预设的信号去噪网络根据信号特征对海底电磁探测信号进行去噪处理，得到去噪后的海底电磁探测信号，信号去噪网络利用海底电磁信噪样本进行训练得到。The denoising module 402 is configured to perform denoising processing on the submarine electromagnetic detection signal according to the signal characteristics by using a preset signal denoising network to obtain a denoised submarine electromagnetic detection signal, and the signal denoising network uses the submarine electromagnetic signal noise samples for training get.

本申请实施例提供的海底电磁信号的处理装置，通过提取模块401对海底电磁探测信号进行信号特征提取，得到海底电磁探测信号的信号特征，从而能够分析出海底电磁探测信号的噪声特征和电磁信号特征，以有针对性地识别海底电磁探测信号中噪声和电磁信号；以及通过信号去噪网络学习复杂海洋环境中的海底电磁探测信号的信号特征，去噪模块402再利用信号去噪网络根据实际探测得到海底电磁探测信号的信号特征，对海底电磁探测信号进行去噪，得到去噪后的海底电磁探测信号，从而能够根据信号去噪网络所学习到的信号特征识别海底电磁探测信号的噪声和电磁信号，并将噪声从海底电磁探测信号中去除，以有针对性地对复杂海洋环境中的海底电磁探测信号进行噪声识别和去噪，进而优化海底电磁探测信号的去噪效果，有效提高海底电磁探测信号的品质。The apparatus for processing submarine electromagnetic signals provided by the embodiments of the present application extracts the signal features of the submarine electromagnetic detection signals through the extraction module 401 to obtain the signal characteristics of the submarine electromagnetic detection signals, so that the noise characteristics and electromagnetic signals of the submarine electromagnetic detection signals can be analyzed. feature to identify noise and electromagnetic signals in submarine electromagnetic detection signals in a targeted manner; and learn the signal characteristics of submarine electromagnetic detection signals in complex marine environments through the signal de-noising network, and the de-noising module 402 then uses the signal de-noising network according to the actual situation. The signal characteristics of the submarine electromagnetic detection signal are detected, and the submarine electromagnetic detection signal is denoised to obtain the denoised submarine electromagnetic detection signal, so as to identify the noise and noise of the submarine electromagnetic detection signal according to the signal characteristics learned by the signal denoising network. Electromagnetic signals, and remove the noise from the submarine electromagnetic detection signals, so as to identify and de-noise the submarine electromagnetic detection signals in a complex marine environment in a targeted manner, thereby optimizing the denoising effect of the submarine electromagnetic detection signals and effectively improving the seabed. The quality of the electromagnetic detection signal.

作为本申请一实施例，信号特征包括海底电磁探测信号的波形特征、梅尔频率倒谱系数和功率谱密度。As an embodiment of the present application, the signal characteristics include waveform characteristics, Mel frequency cepstral coefficients, and power spectral density of the submarine electromagnetic detection signal.

作为本申请一实施例，提取模块401，还用于：As an embodiment of the present application, the extraction module 401 is further used for:

对海底电磁探测信号进行短时傅里叶变换，得到海底电磁探测信号的波形特征；Perform short-time Fourier transform on the submarine electromagnetic detection signal to obtain the waveform characteristics of the submarine electromagnetic detection signal;

对海底电磁探测信号进行梅尔频率倒谱分析，得到海底电磁探测信号的梅尔频率倒谱系数；Perform Mel-frequency cepstral analysis on the submarine electromagnetic detection signal, and obtain the Mel-frequency cepstral coefficient of the submarine electromagnetic detection signal;

对海底电磁探测信号进行傅里叶变换，得到海底电磁探测信号的功率谱密度。Fourier transform is performed on the submarine electromagnetic detection signal to obtain the power spectral density of the submarine electromagnetic detection signal.

作为本申请一实施例，信号处理装置，还包括：As an embodiment of the present application, the signal processing apparatus further includes:

获取模块，用于获取海底电磁信噪样本，海底电磁信噪样本包括信号样本和噪声样本；The acquisition module is used to acquire submarine electromagnetic signal-noise samples, and the submarine electromagnetic signal-noise samples include signal samples and noise samples;

第二提取模块，用于对信号样本和噪声样本进行特征提取，得到信号样本特征和噪声样本特征；The second extraction module is used to perform feature extraction on the signal sample and the noise sample to obtain the signal sample feature and the noise sample feature;

训练模块，用于利用信号样本特征和噪声样本特征对预设机器学习网络进行训练，直至预设机器学习网络达到预设收敛条件，得到信号去噪网络。The training module is used for training the preset machine learning network by using the signal sample feature and the noise sample feature until the preset machine learning network reaches the preset convergence condition, and a signal denoising network is obtained.

作为本申请一实施例，获取模块，还用于：As an embodiment of the present application, the acquisition module is also used for:

获取多种目标天气时的海底电磁实测信号，将海底电磁实测信号作为信号样本；Obtain submarine electromagnetic measured signals in various target weathers, and use submarine electromagnetic measured signals as signal samples;

获取多种海底洋流产生的电磁场信号，将海底噪声作为噪声样本。Obtain the electromagnetic field signals generated by a variety of seafloor currents, and use seafloor noise as a noise sample.

获取预设时间段内的海底电磁实测信号；Obtain the submarine electromagnetic measured signal within a preset time period;

根据目标天气的发生时间段与预设时间段进行匹配；According to the occurrence time period of the target weather and the preset time period;

将预设时间段内与发生时间段匹配的时间段对应的海底电磁实测信号作为信号样本。The submarine electromagnetic measured signal corresponding to the time period matching the occurrence time period within the preset time period is used as the signal sample.

通过电磁场三维正演工具模拟多种海底洋流的洋流运动；Simulate the ocean current movement of various submarine currents through the 3D forward modeling tool of electromagnetic field;

获取每种洋流运动产生的感应电场强度和感应磁场强度；Obtain the induced electric field strength and induced magnetic field strength generated by each ocean current movement;

根据感应电场强度和感应磁场强度，运算得到每种海底洋流产生的电磁场信号作为海底电磁噪声样本。According to the intensity of the induced electric field and the induced magnetic field, the electromagnetic field signal generated by each type of seabed current is obtained by calculation as the sample of seabed electromagnetic noise.

作为本申请一实施例，第二提取模块，还用于：As an embodiment of the present application, the second extraction module is also used for:

提取每种目标天气时的海底电磁实测信号的第一特征，以及提取每种海底洋流产生的电磁场信号的第二特征；Extracting the first feature of the submarine electromagnetic measured signal in each target weather, and extracting the second feature of the electromagnetic field signal generated by each submarine ocean current;

对每种海底电磁实测信号的第一特征进行特征拼接，得到信号样本特征；Perform feature splicing on the first feature of each submarine electromagnetic measured signal to obtain signal sample features;

对每种电磁场信号的第二特征进行特征拼接，得到噪声样本特征。Feature splicing is performed on the second features of each electromagnetic field signal to obtain noise sample features.

需要说明的是，上述装置/单元之间的信息交互、执行过程等内容，由于与本申请方法实施例基于同一构思，其具体功能及带来的技术效果，具体可参见方法实施例部分，此处不再赘述。It should be noted that the information exchange, execution process and other contents between the above-mentioned devices/units are based on the same concept as the method embodiments of the present application. For specific functions and technical effects, please refer to the method embodiments section. It is not repeated here.

所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将所述装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述***中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit, and the above-mentioned integrated units may adopt hardware. It can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the above-mentioned system, reference may be made to the corresponding process in the foregoing method embodiments, which will not be repeated here.

图5为本申请一实施例提供的终端设备的结构示意图。如图5所示，该实施例的终端设备5包括：至少一个处理器50(图5中仅示出一个)处理器、存储器51以及存储在所述存储器51中并可在所述至少一个处理器50上运行的计算机程序52，所述处理器50执行所述计算机程序52时实现上述任意方法实施例中的步骤。FIG. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present application. As shown in FIG. 5 , the terminal device 5 in this embodiment includes: at least one processor 50 (only one is shown in FIG. 5 ), a processor, a memory 51 , and a processor stored in the memory 51 and can be processed in the at least one processor A computer program 52 running on the processor 50, the processor 50 implements the steps in any of the above method embodiments when the computer program 52 is executed.

所述终端设备5可以是手机、桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。该终端设备可包括但不仅限于处理器50、存储器51。本领域技术人员可以理解，图5仅仅是终端设备5的举例，并不构成对终端设备5的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如还可以包括输入输出设备、网络接入设备等。The terminal device 5 may be a computing device such as a mobile phone, a desktop computer, a notebook, a handheld computer, and a cloud server. The terminal device may include, but is not limited to, the processor 50 and the memory 51 . Those skilled in the art can understand that FIG. 5 is only an example of the terminal device 5, and does not constitute a limitation on the terminal device 5. It may include more or less components than the one shown, or combine some components, or different components , for example, may also include input and output devices, network access devices, and the like.

所称处理器50可以是中央处理单元(Central Processing Unit，CPU)，该处理器50还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。The so-called processor 50 may be a central processing unit (Central Processing Unit, CPU), and the processor 50 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuits) , ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

所述存储器51在一些实施例中可以是所述终端设备5的内部存储单元，例如终端设备5的硬盘或内存。所述存储器51在另一些实施例中也可以是所述终端设备5的外部存储设备，例如所述终端设备5上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。进一步地，所述存储器51还可以既包括所述终端设备5的内部存储单元也包括外部存储设备。所述存储器51用于存储操作***、应用程序、引导装载程序(BootLoader)、数据以及其他程序等，例如所述计算机程序的程序代码等。所述存储器51还可以用于暂时地存储已经输出或者将要输出的数据。The memory 51 may be an internal storage unit of the terminal device 5 in some embodiments, such as a hard disk or a memory of the terminal device 5 . The memory 51 may also be an external storage device of the terminal device 5 in other embodiments, such as a plug-in hard disk equipped on the terminal device 5, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, flash memory card (Flash Card), etc. Further, the memory 51 may also include both an internal storage unit of the terminal device 5 and an external storage device. The memory 51 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as program codes of the computer program, and the like. The memory 51 can also be used to temporarily store data that has been output or will be output.

本申请实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现可实现上述各个方法实施例中的步骤。Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

本申请实施例提供了一种计算机程序产品，当计算机程序产品在移动终端上运行时，使得移动终端执行时实现可实现上述各个方法实施例中的步骤。The embodiments of the present application provide a computer program product, when the computer program product runs on a mobile terminal, the steps in the foregoing method embodiments can be implemented when the mobile terminal executes the computer program product.

所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，所述计算机程序包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质至少可以包括：能够将计算机程序代码携带到拍照装置/终端设备的任何实体或装置、记录介质、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质。例如U盘、移动硬盘、磁碟或者光盘等。在某些司法管辖区，根据立法和专利实践，计算机可读介质不可以是电载波信号和电信信号。The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the present application realizes all or part of the processes in the methods of the above embodiments, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When executed by a processor, the steps of each of the above method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include at least: any entity or device capable of carrying the computer program code to the photographing device/terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunication signals, and software distribution media. For example, U disk, mobile hard disk, disk or CD, etc. In some jurisdictions, under legislation and patent practice, computer readable media may not be electrical carrier signals and telecommunications signals.

在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.

在本申请所提供的实施例中，应该理解到，所揭露的装置/网络设备和方法，可以通过其它的方式实现。例如，以上所描述的装置/网络设备实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。In the embodiments provided in this application, it should be understood that the disclosed apparatus/network device and method may be implemented in other manners. For example, the apparatus/network device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units. Or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

以上所述实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the above-mentioned embodiments, those of ordinary skill in the art should understand that: it can still be used for the above-mentioned implementations. The technical solutions described in the examples are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions in the embodiments of the application, and should be included in the within the scope of protection of this application.

Claims

一种信号处理方法，其特征在于，包括：A signal processing method, comprising:

对海底电磁探测信号进行信号特征提取，得到所述海底电磁探测信号的信号特征；performing signal feature extraction on the submarine electromagnetic detection signal to obtain the signal characteristics of the submarine electromagnetic detection signal;

利用预设的信号去噪网络根据所述信号特征对所述海底电磁探测信号进行去噪处理，得到去噪后的海底电磁探测信号，所述信号去噪网络利用海底电磁信噪样本进行训练得到。Use a preset signal de-noising network to de-noise the submarine electromagnetic detection signal according to the signal characteristics to obtain a de-noised submarine electromagnetic detection signal. The signal de-noising network uses submarine electromagnetic signal noise samples to train to obtain .
如权利要求1所述的信号处理方法，其特征在于，所述信号特征包括所述海底电磁探测信号的波形特征、梅尔频率倒谱系数和功率谱密度。The signal processing method according to claim 1, wherein the signal characteristics include waveform characteristics, Mel frequency cepstral coefficients and power spectral density of the submarine electromagnetic detection signal.
如权利要求2所述的信号处理方法，其特征在于，所述对海底电磁探测信号进行信号特征提取，得到所述海底电磁探测信号的信号特征，包括：The signal processing method according to claim 2, wherein the signal feature extraction is performed on the submarine electromagnetic detection signal to obtain the signal characteristics of the submarine electromagnetic detection signal, comprising:

对所述海底电磁探测信号进行短时傅里叶变换，得到所述海底电磁探测信号的波形特征；Performing short-time Fourier transform on the submarine electromagnetic detection signal to obtain the waveform characteristics of the submarine electromagnetic detection signal;

对所述海底电磁探测信号进行梅尔频率倒谱分析，得到所述海底电磁探测信号的梅尔频率倒谱系数；Carrying out Mel frequency cepstrum analysis on the seabed electromagnetic detection signal to obtain the Mel frequency cepstral coefficient of the seabed electromagnetic detection signal;

对所述海底电磁探测信号进行傅里叶变换，得到所述海底电磁探测信号的功率谱密度。Fourier transform is performed on the submarine electromagnetic detection signal to obtain the power spectral density of the submarine electromagnetic detection signal.
如权利要求1所述的信号处理方法，其特征在于，所述利用预设的信号去噪网络根据所述信号特征对所述海底电磁探测信号进行去噪处理，得到去噪后的海底电磁探测信号之前，还包括：The signal processing method according to claim 1, wherein the de-noising process is performed on the submarine electromagnetic detection signal by using a preset signal de-noising network according to the signal characteristics, so as to obtain a de-noised submarine electromagnetic detection signal. Before the signal, also include:

获取所述海底电磁信噪样本，所述海底电磁信噪样本包括信号样本和噪声样本；acquiring the submarine electromagnetic signal-to-noise samples, where the submarine electromagnetic signal-to-noise samples include signal samples and noise samples;

对所述信号样本和所述噪声样本进行特征提取，得到信号样本特征和噪声样本特征；performing feature extraction on the signal samples and the noise samples to obtain signal sample features and noise sample features;

利用所述信号样本特征和所述噪声样本特征对预设机器学习网络进行训练，直至所述预设机器学习网络达到预设收敛条件，得到所述信号去噪网络。The preset machine learning network is trained by using the signal sample feature and the noise sample feature until the preset machine learning network reaches a preset convergence condition, and the signal denoising network is obtained.
如权利要求4所述的信号处理方法，其特征在于，所述获取所述海底电磁信噪样本，包括：The signal processing method according to claim 4, wherein the acquiring the submarine electromagnetic signal-to-noise sample comprises:

获取多种目标天气时的海底电磁实测信号，将所述海底电磁实测信号作为所述信号样本；Obtaining the undersea electromagnetic measured signals in a variety of target weathers, and using the undersea electromagnetic measured signals as the signal samples;

获取多种海底洋流产生的电磁场信号，将所述海底噪声作为所述噪声样本。Electromagnetic field signals generated by various seafloor currents are acquired, and the seafloor noise is used as the noise sample.
如权利要求5所述的信号处理方法，其特征在于，所述获取多种海底洋流产生的电磁场信号，将所述海底噪声作为所述海底电磁噪声样本，包括：The signal processing method according to claim 5, wherein the acquiring electromagnetic field signals generated by a variety of seabed ocean currents, and using the seafloor noise as the seabed electromagnetic noise sample, comprises:

通过电磁场三维正演工具模拟多种所述海底洋流的洋流运动；Simulate the ocean current movement of a variety of the seabed ocean currents through the electromagnetic field three-dimensional forward modeling tool;

获取每种所述洋流运动产生的感应电场强度和感应磁场强度；Obtain the intensity of the induced electric field and the intensity of the induced magnetic field generated by the movement of each of the ocean currents;

根据所述感应电场强度和所述感应磁场强度，运算得到每种所述海底洋流产生的电磁场信号作为所述海底电磁噪声样本。According to the intensity of the induced electric field and the intensity of the induced magnetic field, an electromagnetic field signal generated by each type of the seafloor ocean current is obtained as the seafloor electromagnetic noise sample.
如权利要求4所述的信号处理方法，其特征在于，所述信号样本包括多种目标天气时的海底电磁实测信号，所述噪声样本包括多种海底洋流产生的电磁场信号；The signal processing method according to claim 4, wherein the signal samples include submarine electromagnetic measured signals in various target weathers, and the noise samples include electromagnetic field signals generated by various submarine ocean currents;

所述对所述信号样本和所述噪声样本进行特征提取，得到信号样本特征和噪声样本特征，包括：The feature extraction is performed on the signal sample and the noise sample to obtain the signal sample feature and the noise sample feature, including:

提取每种目标天气时的所述海底电磁实测信号的第一特征，以及提取每种海底洋流产生的所述电磁场信号的第二特征；Extracting the first feature of the submarine electromagnetic measured signal in each target weather, and extracting the second feature of the electromagnetic field signal generated by each submarine ocean current;

对每种所述海底电磁实测信号的第一特征进行特征拼接，得到所述信号样本特征；Perform feature splicing on the first features of each of the submarine electromagnetic measured signals to obtain the signal sample features;

对每种所述电磁场信号的第二特征进行特征拼接，得到所述噪声样本特征。Feature splicing is performed on the second feature of each of the electromagnetic field signals to obtain the noise sample feature.
一种信号处理装置，其特征在于，包括：A signal processing device, comprising:

提取模块，用于对海底电磁探测信号进行信号特征提取，得到所述海底电磁探测信号的信号特征；an extraction module, used for extracting signal features of the submarine electromagnetic detection signal to obtain the signal characteristics of the submarine electromagnetic detection signal;

去噪模块，用于利用预设的信号去噪网络根据所述信号特征对所述海底电磁探测信号进行去噪处理，得到去噪后的海底电磁探测信号，所述信号去噪网络利用海底电磁信噪样本进行训练得到。a de-noising module, configured to perform de-noising processing on the submarine electromagnetic detection signal according to the signal characteristics by using a preset signal de-noising network to obtain a de-noised submarine electromagnetic detection signal, and the signal de-noising network uses the submarine electromagnetic detection signal Signal-to-noise samples are obtained by training.
一种终端设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至7任一项所述的方法。A terminal device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, when the processor executes the computer program, the process according to claim 1 to 7. The method of any one.
一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至7任一项所述的方法。A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.