RU2543567C2 - Method of character synchronisation when receiving code pulse modulation or frequency keying with familiar structure - Google Patents

Abstract

FIELD: radio engineering, communication.

SUBSTANCE: search of informational signal binary character limits involves two-level processing of an input signal. At the first level, the search of the character sequence limit is performed using FFT and calculation of coefficients for correlation between an instantaneous spectrum and frequency images of the information characters, as well as a frequency image of the character differentiation. If the spectrum "spreading" is registered, then strobe signals are generated and sent to a run-down generator of the character frequency to generate reference pulses of the character synchronisation. The second level involves the determination of the received information message character nominal value using a two-channel demodulating circuit, and generation of a synchronous code sequence. As a result, the processes of the character limit search and received binary character demodulation are transferred from the temporal field to the time-and-frequency field.

EFFECT: lower locking in synchronism duration.

5 dwg

Description

The invention relates to radio engineering and can be used in radio telemetry systems when receiving telemetric information.

Currently, all existing synchronization methods in information and telemetry systems are implemented in the time domain. Due to the increase in the speed of information transmission, the influence of intentional and unintentional interference, the probability of accurately determining the sequence of characters in the information message is reduced. Inaccurate determination of the boundaries of the characters leads to the loss of telemetric information. To minimize the loss of telemetric information, a synchronization method in the time-frequency domain is proposed. The analysis of the methods showed the possibility of processing the signal in the time-frequency domain [1-3]. These patents describe methods based on the use of Fourier transform, wavelet analysis, neural networks, used for signal demodulation. These methods do not disclose synchronization issues.

A known method of improved synchronization of linearly-frequency-modulated sequences [1]. The invention discloses methods and devices for identifying correct peaks in the output signals of matched filters. The received signal correlates with a copy of the synchronization signal, thereby forming a correlation output signal. Peaks are detected in the correlation output. The peak is tested at a set of predetermined locations, which are set by the properties of the synchronization signal, thereby generating a lot of signal testing signals peaks [1].

This method is used to synchronize cellular signals using digital signal processing algorithms. Its disadvantage is that it is not applicable to the structure of the symbol synchronization of a group telemetric signal.

In [2], a signal recognition method based on the fast Fourier transform is proposed.

This approach has a drawback expressed in the use of several tuning loops with full recognition of the input signal. This leads to the inability to process signals in the mode of direct reception of information.

Closest to claim 1 of the formula for solving synchronization issues in information and telemetry systems is a method for recognizing and demodulating a signal with an unknown structure [3], which is selected as a prototype. This approach to signal recognition and demodulation is based on the use of a two-level signal processing circuit. Initially, primary wavelet processing is carried out for a rough estimation of signal parameters (maximum, minimum amplitudes and frequencies), and the presence of phase distortions. For accurate determination of signal parameters, secondary analysis by neural networks and automatic adjustment for each type of input signal are used. Achievable technical result is the determination of parameters and demodulation of a signal with an unknown structure based on a self-learning neural network. Moreover, the accuracy of signal processing is limited by the noise components of the input signal [3]. This method can be used to solve the problem of increasing the stability of synchronization. Its disadvantage is the difficulty of developing formalized tuning algorithms and determining the optimal structure of a neural network.

In the proposed method, by analogy with the prototype, character boundaries are recognized and the telemetry information signal is demodulated by KIM ₂ -FM modulation using a two-level signal processing circuit. In this method, to eliminate the disadvantages of the prototype, instead of the neural network, a fast Fourier transform algorithm is used, with the help of which information is obtained from the instantaneous spectrum of the signal, necessary to determine the boundaries of the characters and demodulate the information message in the mode of direct reception of information. The analytical representation of the signal with modulation KIM ₂ -FM is described by the following mathematical formula:

S (t) = S _m cos (2πf _i t + φ), i = 1,2, (1)

Where

S (t) is the transmitted signal;

S _m is the amplitude of the modulated signal;

t is the value of time;

φ is the phase shift of the signal;

f _i is the frequency of the information symbol;

i is the frequency index.

In binary coding, a frequency-shift key is transmitted at two different frequencies.

A graphical view of a signal simulated in a Matlab environment with modulation of CMM _2- FM is shown in figure 1.

The proposed method is based on the application of the Fourier transform of the received signal. Mathematically, the Fourier transform is described by the following formula:

$$\dot{S}\left(\omega \right)={\displaystyle \underset{-\infty }{\overset{\infty }{\int }}S\left(t\right)e^{-j\omega t}dt,\text{(2)}}$$

Where

- спектральная функция сигнала S(t); $$\dot{S}\left(\omega \right)$$

- spectral function of the signal S (t);

ω = 2πf is the circular frequency.

Information message "0""1" with modulation KIM ₂ -FM in the spectral region is presented in figure 2.

From figure 2 it is seen that the amplitude of the spectrum is maximum at the nominal frequencies of the transmitted symbols.

Figure 3 shows the spectra of single information symbols.

Currently, when processing a signal in the frequency domain, the spectrum of the entire received signal is analyzed, as a result of which copies of the spectrum appear in the frequency domain and intersymbol interference occurs. The use of the Fourier transform over the entire time interval of signal reception does not allow for simultaneous processing in the frequency and time domain. The essence of the application of the developed method for synchronizing information and telemetry systems is to build instantaneous spectra from sections of the received signal in the mode of direct reception of information. This will allow us to relate the analysis of the signal in the frequency domain with time and to avoid the appearance of copies of the spectrum. Information symbols of the signal with modulation KIM ₂ -FM differ from each other by the nominal frequency of the transmission. When constructing instantaneous spectra, the transition from one symbol to another is characterized by the "spreading" of the spectrum on the frequency axis. This fact is confirmed by the simulation results in the Matlab environment. A graphical view of the simulation results is presented in figure 4.

The phenomenon of “spreading” of the spectrum is mathematically described as follows. The Fourier transform formula in discrete form is as follows:

$$S\left(m\right)={\displaystyle \sum _{n=0}^{N-\mathrm{one}}S\left(n\right)\left[\cos \left(2\pi mn/N\right)-j\sin \left(2\pi mn/N\right)\right],\text{(3)}}$$

Where

S (m) is the mth component of the discrete Fourier transform;

m is the index of the discrete Fourier transform in the frequency domain, m = 0, 1, 2, 3, ... N-1;

S (n) is a sequence of discrete samples of the input signal;

n is the time index of the input samples, n = 0, 1, 2, 3, ... N-1;

j is the imaginary unit;

N is the number of samples of the input sequence and the number of frequency samples of the result of the discrete Fourier transform.

The indices of the input values of n and the output samples of the Fourier transform m always take values from 0 to N-1. This means that if there are N input samples in the time domain, the Fourier transform calculates the spectral composition at N uniformly distributed points of the frequency axis. The value of N determines the required number of input samples, the resolution of the Fourier transform in frequency.

The resolution f _s / N determines the distance in frequency between the samples of the Fourier transform. When constructing the signal spectrum, instead of the resolution, the values of the analyzed frequencies of the Fourier transform are calculated using the following formula:

f _an (m) = (mf _s ) / N, (4)

Where

f _an - analyzed frequencies;

m is the index of the discrete Fourier transform in the frequency domain, m = 0, 1, 2, 3, ... N-1;

f _s - signal sampling rate;

N is the number of frequency samples of the result of the discrete Fourier transform.

As a result of the Fourier transform of the received signal, a series of S (m) values are calculated at the analyzed frequencies f _an , which are the values of the amplitude of the spectrum of the received signal. The analysis frequencies remain constant, since the values of m, f _s , N are constant. When analyzing the signal S (t), the values of the amplitude of the spectrum S (m) do not change until the signal S (t) is transmitted by the frequency value f ₁ . As soon as samples with a frequency nominal value f ₂ appear in the sequence of discrete samples of the signal S (t), the values of the amplitude of the spectrum S (m) change, as a result of which the spectrum “spreads”.

Fixing the moments of the beginning of the spreading of the spectrum, the clock generator generates clock pulses supplied to the input of the code sequence forming device. At the second processing level of the received signal, the instantaneous spectrum between the boundaries of the symbols of the information message is calculated. The calculated instantaneous spectrum is compared in the decision-making device with the frequency image of the symbol (a series of values of the spectral components). As a result of the comparison, the deciding device makes a decision on the nominal value of the symbol and transmits the nominal value of the symbol to the code sequence generating device. The code sequence generator generates

synchronized binary pulses of the video frequency. From the output of the device generating the code sequence information is received for further processing.

Figure 5 presents a schematic representation of the method of symbol synchronization in the time-frequency domain of the signal with modulation KIM ₂ -FM, where

1. PR - receiver;

2. IF - frequency converter;

3. KP - tuning loop;

4. D - discretizer;

5. G1 - sample rate generator;

6. PC - shift register;

7. UVMS - device for calculating the instant spectrum;

8. "0" - a storage device for the frequency components of the symbol "0";

9. “1” - a storage device for the frequency components of the symbol “1”;

10. "01" - a storage device for the frequency components of the differential characters;

11. RU - decisive device;

12. UVKK - device for calculating the correlation coefficient;

13. G2 - symbol frequency generator;

14. URS - a device for deciding on the meaning of a symbol

15. UFKP - device for generating a code sequence.

In accordance with the scheme of the method, the following sequence of actions is performed:

1. The input radio signal modulation KIM ₂ -FM is fed to the input of the receiving device.

2. At the receiver, the signal is transferred to the intermediate frequency.

3. In the tuning loop, the Doppler frequency shift is calculated according to the known values of the frequencies of the transmitted symbols of the information message stored in it.

4. The values of the Doppler frequency shift are transmitted to the storage devices of the frequency images of the symbol and the difference of characters (series of values of the spectral components), where the values of the spectral components of the information symbol are recalculated taking into account the Doppler shift.

5. In the sampler, the intermediate frequency information signal is sampled in accordance with the frequency generated by the sample rate generator. As a result of sampling, a plurality of N discrete samples are stacked on the duration of the information symbol of the radio signal. N = {N ₁ , N ₂ , ... N _k }, where k is an integer, a positive number and is calculated based on a given sampling frequency. The sampling rate is set by the operator.

6. The values of the discrete samples are fed to the inputs of the shift registers of the demodulator and the device for determining the boundaries of characters.

7. In the device for determining the boundaries of characters, a plurality of N discrete samples of the information signal are accumulated in the register. Based on the accumulated samples, the instant spectrum calculator calculates the instant spectrum, which is compared in the comparison and decision-making device with the frequency images “0”, “1” and the character difference. Each subsequent incoming discrete sample N _{k + 1} forces out the sample stored in it from the register. With each new incoming sample, the operation of calculating the instantaneous spectrum and comparing it with frequency images is performed. The results of the comparison are the values of the correlation coefficients.

8. The search for the symbol boundary in the comparison and decision-making device begins with determining the maximum correlation coefficient of the instant spectrum with the image of one of the symbols. In the case of successive identical code values at the same input signal level, the calculated values of the correlation coefficient remain constant. Upon receipt of a discrete sample N _j in the register, which is a discrete sample of the character following the processed one and having the opposite value (changing the code message from “0” to “1” or from “1” to “0”), the spectrum “spreads”. The spreading of the spectrum is characterized by a decrease in the correlation coefficient. The comparison and decision-making device fixes the temporary position N _{j of the} discrete sample as the boundary of the symbol and verifies this assumption by calculating the correlation coefficients of the instantaneous spectra with the difference of symbols and the image of the symbol having the opposite value. To confirm the assumption of the detected boundary of the symbol, two conditions are checked. Firstly, the maximum moment of the correlation coefficient of the instant spectrum with the image of the symbol difference should occur through k / 2 processed discrete samples, starting from the moment the spectrum spreads, that is, on the sample N _{(j + k / 2)} . Secondly, the maximum moment of the correlation coefficient of the instant spectrum with the image of the opposite symbol should occur through k discrete samples from the assumed boundary of the symbol. When these conditions are met, the final decision is made that the temporary position N _{j of the} discrete reference is the boundary of the information symbol. Having determined the moment of time of the boundary of the symbols, the device for comparison and decision making produces strobe signals supplied to the input of the inertial generator of the symbol frequency. When the information content of the received signal changes, the value of k is recalculated, the coincidence of the time moment k / 2 and the maximum of the correlation coefficient of the instant spectrum with the image of the symbol difference is checked, and the output of strobe signals is adjusted.

9. After determining the boundaries of the symbols, the decider adjusts the shift register of the demodulator to analyze M discrete samples of the information symbol. The number M of discrete samples is determined by the decider in such a way that they do not include discrete samples of another information symbol and samples falling within the intersymbol interference interval. M = {M ₁ , M ₂ , ... M _r }, where r <k and r is an integer, a positive number.

10. The device for calculating the instantaneous spectrum of the demodulator calculates the instantaneous spectrum from the received M discrete samples.

11. In devices for calculating the correlation coefficient, the value of the correlation coefficient of the instant spectrum with images of information symbols (a series of values of spectral components) is calculated.

12. The device for deciding on the value of the symbol makes a decision on the nominal value of the information symbol by comparing the correlation coefficients of the instantaneous spectrum with the image “0” and “1” and choosing a larger value, after which it issues this decision to the code sequence generation device.

13. In the inertial symbol frequency generator, reference symbol synchronization pulses are formed corresponding to the symbol boundary by extracting from the sequence of pulses controlling the sampling of the continuous input radio signal received from the sampling frequency generator at the times of receiving the strobe signals. Pulses of symbol synchronization are fed to the device for generating a code sequence. The inertia of the symbol frequency generator is due to the need to preserve the symbol frequency when receiving code combinations with a set of symbols of the same value, when the symbol boundary cannot be determined.

14. The device for generating a code sequence generates binary pulses of a video frequency with a duration determined by an inertial generator of symbol frequency.

15. From the output of the device for generating a code sequence, information in the form of a binary code accompanied by pulses of a symbolic frequency enters the circuit for further processing of information.

The technical result of the invention is a method for symbolic synchronization of terrestrial receiving and recording equipment of telemetric information when receiving a signal with modulation of CMM _2- FM in the time-frequency domain.

The novelty of the invention lies in a new approach to the symbol synchronization process, the transfer of the synchronization process from the time domain to the time-frequency domain.

The inventive step is characterized by the use of the previously known mathematical apparatus of the Fourier transform to solve the problem of finding the boundaries of the information symbols of a message and identifying patterns when calculating instantaneous spectra at these boundaries.

Industrial applicability - this invention is industrially applicable, as it can be implemented on existing programmable logic integrated circuits.

Information sources

1. Patent RU 2472295 C2, H04L 27/26, publ. 01/10/2013. Improved synchronization of linear frequency modulated sequences.

2. Patent RU 2216748 C2, G01R 23/16, publ. 11/20/2003. A method for recognizing signals of radio communication systems.

3. Patent RU 2386165 C2, G06F 17/14, G06N 3/02, G01R 23/16, publ. 04/10/2010. A method for determining the structure and demodulation of a signal with an unknown structure.

4. Sergienko A.B. Digital signal processing: a training manual / A.B.Sergienko. - 3rd ed. - SPb .: BHV-Petersburg, 2011 .-- 768 p.

5. Manovtsev A.P. Introduction to digital radio telemetry / A.P. Manovtsev. - Moscow: Energy, 1967 .-- 343 p.

Claims (1)

The method of symbol synchronization upon receipt of a code-pulse modulation signal - frequency manipulation with a known structure, which consists in determining the boundaries of the binary code sequence symbols and demodulating the received information symbols, characterized in that the symbol synchronization process is carried out in the time-frequency domain using a two-level signal processing circuit using fast Fourier transform algorithm of a discretized radio signal, where at the first processing level they search for the boundaries of information symbols based on the calculation of the correlation coefficients of the instant spectrum with the frequency images of information symbols “0” and “1” and the difference of characters from “0” to “1” or from “1” to “0”, at the same time fixing the beginning of the “spreading” of the spectrum, produce strobe signals, form reference pulses of symbol synchronization, and at the second signal processing level, information symbols are demodulated based on the calculation of the correlation coefficients of the instant spectrum from the signal fragment, respectively favoring the duration of the information symbol to the frequency of binary images of characters.

Images