Signal processing system, method and device based on computer

Abstract

The invention relates to the technical field of computer signal processing, in particular to a signal processing system, method and device based on a computer, and the system comprises a high-precision collection module which is used for collecting signals; the distributed processing module is used for realizing distributed acquisition and processing of signals; the multi-signal fusion module is used for carrying out fusion processing on the acquired different types of signals; the real-time signal early warning module is used for monitoring and early warning abnormal signals in real time; the analog signal simulation module is used for generating an analog signal through a computer simulation technology so as to simulate a real environment; and the intelligent diagnosis and maintenance module is used for carrying out monitoring and fault diagnosis on the running state of the system through a long-short-term memory network and providing maintenance reminding. According to the invention, high-precision acquisition of signals can be realized, monitoring requirements in a complex environment are met, the accuracy and reliability of signal processing are improved, and the risk of device faults and the maintenance cost are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of computer signal processing, and in particular to a computer-based signal processing system, method and device. Background Art

[0002] Signal processing systems play a vital role in modern industrial, military and environmental monitoring fields. Traditional signal processing systems usually rely on a single sensor or a centralized processing architecture, which has many limitations when processing multi-source signals in complex environments. For example, in nuclear, biological and chemical monitoring, industrial automation and environmental monitoring scenarios, a single sensor often cannot provide comprehensive information, while a centralized processing architecture is difficult to meet the requirements of real-time and high efficiency.

[0003] Existing signal processing systems have significant deficiencies in many aspects. First, the signal acquisition accuracy and response speed of traditional systems cannot meet the needs of high-sensitivity monitoring, especially in complex nuclear, biological and chemical environments, where slight changes in signals may indicate potential dangers. Second, centralized processing architectures are prone to data transmission delays and processing bottlenecks when processing large amounts of data in distributed sensor networks. In addition, existing systems have limited capabilities in signal fusion and fault diagnosis, and are unable to effectively integrate multi-source signals and perform real-time warnings and intelligent maintenance.

[0004] In order to solve the deficiencies of the prior art, the present invention proposes a computer-based signal processing system, method and device. Summary of the invention

[0005] The purpose of the present invention is to solve the problem of trivial and complicated calculation process and large calculation workload in the prior art and to propose a computer-based signal processing system, method and device.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a computer-based signal processing system, comprising: High-precision acquisition module, which collects signals through sensors and analog-to-digital converters; Distributed processing module, which realizes distributed signal collection and processing through network connection and edge computing technology; Multi-signal fusion module, which performs fusion processing on different types of collected signals through feature extraction and fusion algorithm; The real-time signal warning module uses support vector machines to analyze signals in real time, thus achieving real-time monitoring and warning of abnormal signals; Analog signal simulation module, which generates analog signals through computer simulation technology to simulate the real environment; The intelligent diagnosis and maintenance module monitors the system operation status and diagnoses faults through long short-term memory networks, and provides maintenance reminders.

[0007] Furthermore, the computer-based signal processing method comprises the following steps: Step S1, collecting toxicant concentration, radiation intensity, biological signals, temperature, humidity and pressure signals through a high-precision acquisition module; Step S2, realizing distributed signal collection through a distributed processing module, and performing preliminary data processing at edge nodes using edge computing technology to reduce data transmission volume; Step S3, fusing the collected signals of different types through a multi-signal fusion module, extracting key features and generating a comprehensive signal; Step S4, using a real-time signal warning module to analyze the fused signal in real time, detect anomalies and issue a warning; Step S5, generating a simulated signal by a simulated signal simulation module to simulate a real environment, so as to test and verify the performance of the signal processing system; Step S6, monitor the system operation status and diagnose faults through the intelligent diagnosis and maintenance module, generate maintenance suggestions and remind users.

[0008] Furthermore, the computer-based signal processing device comprises: A multi-sensor interface, used to connect a toxic agent concentration sensor, a radiation intensity sensor, a biological signal sensor, a temperature sensor, a humidity sensor, and a pressure sensor, wherein the multi-sensor interface supports multiple sensor types and communication protocols; An input interface, used to connect a sensor and receive a signal, wherein the input interface supports a variety of sensor interface standards, including SPI, I2C, and UART; A network interface, used to realize real-time transmission and distributed processing of data, the network interface supports Ethernet and Wi-Fi communications; A processor, used to execute the signal processing method, wherein the processor is a multi-core processor and supports parallel processing; A memory, used to store the collected signals, processing results and models, the memory including 16GB of RAM and a 512GB solid-state hard disk; An output interface, used to output processing results and warning information, the output interface supports a variety of display and communication interfaces, including HDMI, USB and Ethernet; A user interface, used to display signal processing results, warning information and device status, wherein the user interface supports touch screen operation and remote access; A display module, used to display signal processing results and system status, wherein the display module is an LCD display screen; A communication module is used to realize distributed transmission and processing of signals, and the communication module supports wired and wireless communication protocols, including Ethernet, Wi-Fi and 5G.

[0009] Compared with the prior art, the present invention has the following beneficial effects: The present invention can realize high-precision acquisition of multiple signals through a high-precision acquisition module, which not only has higher acquisition accuracy, shorter response time, and lower error, but also significantly improves the quality and reliability of the signal, and can better meet the monitoring needs in complex environments.

[0010] The present invention realizes distributed acquisition and processing of signals through distributed processing modules, which not only improves the response speed of the system, but also significantly reduces data transmission delays and processing bottlenecks. It can more efficiently process data in large-scale distributed sensor networks, support higher data transmission rates, and have stronger scalability and flexibility.

[0011] The present invention can effectively fuse different types of signals through a multi-signal fusion module, which not only improves the accuracy and reliability of signal processing, but also can extract more valuable information.

[0012] The present invention uses an intelligent diagnosis and maintenance module to monitor the system operating status in real time and receive maintenance reminders in a timely manner, which significantly improves the reliability and maintenance efficiency of the system and reduces the risk of device failure and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0014] Figure 1 A schematic diagram of a system structure provided by an embodiment of the present invention; Figure 2 A schematic diagram of a method flow chart provided by an embodiment of the present invention; Figure 3 A schematic diagram of the device structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the computer-based signal processing system, method and device proposed by the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0016] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0017] The following examples are for illustrative purposes only and are not intended to limit the scope of the present invention.

[0018] The specific scheme of the computer-based signal processing system, method and device provided by the present invention is described in detail below with reference to the accompanying drawings.

[0019] Example Please refer to Figure 1 : is a schematic diagram of a system structure provided by an embodiment of the present invention, which provides a computer-based signal processing system in an embodiment of the present invention, including: High-precision acquisition module, which collects signals through sensors and analog-to-digital converters; Distributed processing module, which realizes distributed signal collection and processing through network connection and edge computing technology; Multi-signal fusion module, which performs fusion processing on different types of collected signals through feature extraction and fusion algorithm; The real-time signal warning module uses support vector machines to analyze signals in real time, thus achieving real-time monitoring and warning of abnormal signals; Analog signal simulation module, which generates analog signals through computer simulation technology to simulate the real environment; The intelligent diagnosis and maintenance module monitors the system operation status and diagnoses faults through long short-term memory networks, and provides maintenance reminders.

[0020] 1. High-precision acquisition module The high-precision acquisition module includes a signal collection unit, an analog-to-digital conversion unit, and a signal conditioning unit; The signal collection unit includes a toxic agent concentration sensor, a radiation intensity sensor, a biological signal sensor, a temperature sensor, a humidity sensor, and a pressure sensor, which are used to collect signals. The response time of the collection is no more than 1 second and the error is less than 1%; An analog-to-digital conversion unit, including an analog-to-digital converter, for converting the collected analog signal into a digital signal, the analog-to-digital converter having a 16-bit resolution and a sampling rate of 100 kHz; The signal conditioning unit includes a filtering circuit and an amplifying circuit, which are used to filter, amplify and normalize the collected signal. The filtering circuit adopts a low-pass filter with a cut-off frequency of 10 Hz, and the gain range of the amplifying circuit is 1-100 times.

[0021] It should be noted that the specific indicators of sensor sensitivity and accuracy are: Toxic agent concentration sensor: The sensitivity is that the output signal change per ppm change is not less than 10mV / ppm, the detection limit is 0.01ppm, the response time is not more than 1 second, and the measurement accuracy is ±0.1%.

[0022] Radiation intensity sensor: The sensitivity is that the output signal change for each mSv / h change is not less than 5mV / mSv / h, the detection limit is 0.01mSv / h, the response time does not exceed 1 second, and the measurement accuracy is ±0.5%.

[0023] Biosignal sensor: The sensitivity is that the output signal change per μV change is not less than 1mV / μV, the detection limit is 0.1μV, the response time is not more than 1 second, and the measurement accuracy is ±0.2%.

[0024] Temperature sensor: The sensitivity is that the output signal change per °C change is not less than 10mV / °C, the detection limit is 0.1°C, the response time is not more than 1 second, and the measurement accuracy is ±0.2°C.

[0025] Humidity sensor: The sensitivity is that the output signal changes by no less than 5mV / % for every 1% change, the detection limit is 0.1%, the response time does not exceed 1 second, and the measurement accuracy is ±1%.

[0026] Pressure sensor: The sensitivity is that the output signal change per kPa change is not less than 10mV / kPa, the detection limit is 0.1kPa, the response time does not exceed 1 second, and the measurement accuracy is ±0.5kPa.

[0027] 16-bit resolution: 16-bit resolution means that the analog-to-digital converter can convert the analog signal into 65536 (2^16) different digital values, which can capture tiny changes in the signal.

[0028] 100kHz sampling rate: A sampling rate of 100kHz means that the analog-to-digital converter can sample 100,000 times per second, allowing the analog-to-digital converter to capture 50kHz signals, covering the common signal frequency range in most industrial and environmental monitoring, ensuring that rapid changes in signals are captured in a timely manner, thereby achieving rapid response.

[0029] The cutoff frequency of the low-pass filter is 10Hz: The main function of the low-pass filter is to remove high-frequency noise. By setting the cutoff frequency to 10Hz, high-frequency noise can be effectively removed, the main characteristics of the signal can be retained, and high-precision processing of the signal can be ensured. The gain range of the amplifier circuit is 1-100 times: for weak signals, high gain is required to enhance the signal strength, and the gain range of 1-100 times can meet the needs, ensuring that the signal will not lose important information due to being too weak in subsequent processing; for strong signals, low gain is required to avoid signal saturation, and the gain range of 1-100 times can be flexibly adjusted to ensure that the signal is within the appropriate range.

[0030] 2. Distributed Processing Module The distributed processing module includes a network connection unit, a data transmission unit and a distributed computing unit; Network connection unit, which connects sensors and real-time signal processing units through wired and wireless networks to build a distributed signal processing network. Wired networks include Ethernet, fiber optic communication, industrial bus and serial communication, and wireless networks include Wi-Fi, 5G, ZigBee, Bluetooth, LoRa and NB-IoT; Data transmission unit, used to realize signal transmission, and supports data compression, data encryption and data verification functions. The transmission rate is higher than 100Mbps. Data compression includes Huffman coding, wavelet transform and discrete cosine transform DCT. Data encryption includes advanced encryption standard AES, asymmetric encryption algorithm RSA and elliptic curve encryption algorithm ECC. Data verification includes cyclic redundancy check CRC, CRC32 and parity check. Distributed computing units are used to realize distributed processing of signals. Distributed processing includes preliminary data processing at edge nodes through edge computing technology to reduce the amount of data transmission, and then uploading the processed results. Preliminary data processing includes data preprocessing, feature extraction and simple analysis.

[0031] It should be noted that a wired network refers to a network that transmits data through physical media (cables, optical fibers). The physical media provides a stable connection and a high data transmission rate. It has the characteristics of high stability, fast transmission rate, and strong security. It is used in local area networks (LANs), wide area networks (WANs), and data centers in scenarios that require high data transmission rates and stability.

[0032] Wireless network: refers to a network that transmits data via radio waves. It does not require physical media to connect devices. It has the characteristics of high flexibility, simple deployment and low cost. It is used in mobile communications, the Internet of Things, smart homes and remote offices.

[0033] The classification of wireless networks includes wireless wide area network (WWAN): with wide coverage, which can span cities or even countries; wireless local area network (WLAN): used in local areas of homes, offices or schools; wireless personal area network (WPAN): with a smaller coverage, usually within 10 meters; wireless metropolitan area network (WMAN): with a coverage range between WLAN and WWAN, used in cities or large campuses; wireless body area network (WBAN): used to connect medical monitoring devices attached to the human body.

[0034] Data transmission rate is an important indicator to measure the speed of data transmission. It is measured in Mbps (megabits per second) and represents the amount of data transmitted per unit time. It is a key parameter for evaluating network performance. A higher data transmission rate means that more data can be transmitted in the same amount of time, thereby improving overall transmission efficiency.

[0035] Data transmission rate is higher than 100Mbps: A data transmission rate of 100Mbps can meet the needs of most scenarios and is the baseline for efficient transmission. A data transmission rate higher than 100Mbps can support multiple devices online at the same time and meet the needs of large-scale device connections.

[0036] Data compression is a technique for reducing the amount of data by converting the original data into a more compact form through a specific algorithm while retaining the original information or characteristics of the data.

[0037] Huffman coding: It is a lossless data compression algorithm that builds an optimal binary tree (Huffman tree) based on the frequency of characters in the data and uses this tree to encode the characters. Characters with high frequency use shorter codes, while characters with low frequency use longer codes, which can effectively reduce the overall size of the data.

[0038] Wavelet transform: It is a mathematical tool that analyzes and compresses signals by decomposing them into wavelets of different frequency components. It is suitable for the compression of image and audio signals. It can capture the local features of the signal and retain these features during the compression process.

[0039] Discrete cosine transform DCT: It is a mathematical transform that converts signals from the spatial domain to the frequency domain. It is suitable for image and video compression and can remove redundant information in the image while retaining the main features of the image.

[0040] Data encryption is a method of protecting data security by converting raw data into ciphertext that cannot be directly understood to prevent unauthorized access.

[0041] Advanced Encryption Standard AES: A symmetric encryption algorithm that uses the same key for encryption and decryption. It is efficient and secure and is widely used in various encryption scenarios.

[0042] Asymmetric encryption algorithm RSA: is an asymmetric encryption algorithm based on the problem of large number decomposition. It uses a pair of keys (public key and private key) for encryption and decryption. The public key is used to encrypt data, while the private key is used to decrypt data.

[0043] Elliptic Curve Cryptography (ECC): It is an asymmetric encryption algorithm based on the mathematical structure of elliptic curves. It can provide security comparable to that of RSA using a smaller key length.

[0044] Data validation is a method to ensure data integrity and accuracy by adding checksums during data transmission or storage to detect data errors.

[0045] Cyclic Redundancy Check (CRC): It is a verification method based on polynomial division. It generates a check code by treating the data as a polynomial and calculating the remainder. The receiver can use the same polynomial to verify the integrity of the data.

[0046] CRC32: It is a variation of the CRC algorithm that uses a 32-bit checksum to detect data errors.

[0047] Parity check: It is a simple data verification method that detects errors by checking whether the number of 1s in the data is odd or even.

[0048] Edge computing technology is a distributed computing architecture that moves data processing, storage, and service functions closer to the edge where data is generated, rather than relying entirely on centralized data centers or cloud computing platforms. Edge locations refer to any place where data is generated or close to the source of data generation, including mobile devices, IoT devices, gateways, and small data centers. Preliminary data processing: including data preprocessing, feature extraction and simple analysis. Data preprocessing mainly involves cleaning, denoising and formatting the original data to improve the quality and availability of the data; feature extraction is to extract useful features and information from the data for subsequent analysis and processing; simple analysis is to conduct preliminary analysis and judgment of the data to discover the patterns and anomalies of the data.

[0049] 3. Multi-signal fusion module The multi-signal fusion module includes a feature extraction unit, a fusion processing unit and a fusion algorithm selection unit; The feature extraction unit uses wavelet transform and Fourier transform algorithms to extract key features from the collected signals. The key features include frequency features, time domain features and waveform features. A fusion processing unit, which fuses the extracted features through a fusion algorithm to achieve signal fusion. The fusion algorithm includes weighted average, Bayesian fusion and convolutional neural network; The fusion algorithm selection unit selects a fusion algorithm based on the signal type, and the signal type includes a toxic agent concentration signal, a radiation intensity signal, a biological signal, a temperature signal, a humidity signal and a pressure signal.

[0050] It should be noted that wavelet transform is a mathematical tool that can decompose signals into components of different frequencies and scales. Through wavelet transform, frequency characteristics can be extracted from the signal, which can reflect the energy distribution of the signal at different frequencies.

[0051] Fourier transform: It is a mathematical tool that can convert signals from the time domain to the frequency domain. Through Fourier transform, the spectrum of the signal can be obtained to extract the frequency characteristics. It can also be used to extract time domain characteristics, including the mean, variance, and peak value of the signal.

[0052] Key features: The extracted key features include frequency features, time domain features and waveform features. Frequency features reflect the characteristics of the signal in the frequency domain, time domain features describe the change law of the signal in time, and waveform features reflect the shape and structure of the signal.

[0053] Weighted average: It is a simple fusion algorithm that performs weighted summation of features according to the weight of each signal. It is suitable for situations where the correlation between signals is strong.

[0054] Bayesian fusion: Based on Bayesian theorem, fusion is achieved by calculating the posterior probability of each signal. It can handle the uncertainty between signals and improve the accuracy of the fusion results.

[0055] Convolutional Neural Network: It is a deep learning algorithm that can extract higher-level signals from features through learning. In signal fusion, it can be used to extract and fuse complex feature patterns.

[0056] Toxic agent concentration signal: The concentration signal of chemical agents has a clear threshold and has high real-time requirements. The fusion algorithm selects the Bayesian fusion algorithm, which is suitable for processing uncertain data and can update the posterior probability based on prior knowledge and observation data, thereby providing accurate estimation of the toxic agent concentration.

[0057] Radiation intensity signal: The radiation intensity signal has continuity and high sensitivity. The fusion algorithm selects the weighted average algorithm and the convolutional neural network. The weighted average algorithm is simple and easy to implement, and is suitable for situations where the radiation intensity signal changes relatively smoothly. The convolutional neural network can handle more complex radiation intensity change patterns and improve the accuracy of the fusion results.

[0058] Biological signals: including heart rate, electroencephalogram, and electromyogram, which are characterized by nonlinearity, non-stationarity, and high noise. The fusion algorithm selects convolutional neural network, which can automatically extract complex features in biological signals and process noise and interference in the signals, thereby improving the accuracy and robustness of the fusion results.

[0059] Temperature signal: The temperature measurement signal of the environment or object is continuous and stable, but is affected by environmental noise. The fusion algorithm selects the weighted average algorithm, which is suitable for situations where the temperature signal changes relatively smoothly and the noise is small.

[0060] Humidity signal: The ambient humidity measurement signal is continuous and stable and is affected by environmental noise. The fusion algorithm selects the weighted average algorithm for fusion processing, which can handle the noise and interference in the humidity signal and improve the accuracy of the fusion result.

[0061] Pressure signal: atmospheric pressure or liquid pressure measurement signal, which is real-time and dynamic. The fusion algorithm selects convolutional neural network, which can handle more complex pressure change patterns and adapt to different working environments and conditions.

[0062] 4. Real-time signal warning module The real-time signal warning module includes a real-time signal processing unit, an intelligent analysis unit and a warning decision unit; Real-time signal processing unit, used to process the collected signals in real time, using FPGA to accelerate the signal processing process and achieve signal processing with a delay of less than 10 milliseconds; Intelligent analysis unit, which uses support vector machine to perform real-time analysis and anomaly detection on signals. Real-time analysis includes pattern recognition, trend analysis and signal classification, and anomaly detection includes pattern anomaly detection, trend anomaly detection and signal anomaly recognition; The early warning decision unit determines whether to issue an early warning signal based on the analysis results. The early warning signal includes the alarm type and alarm content. The alarm types include sound alarms, visual alarms and vibration alarms. The alarm content includes the abnormality type, abnormality location, abnormality severity and recommended measures.

[0063] It should be noted that FPGA acceleration: Field Programmable Gate Array (FPGA) is a hardware accelerator that allows multiple tasks to be processed in parallel, thereby significantly increasing the speed of signal processing.

[0064] Processing delay less than 10 milliseconds: Processing delay less than 10 milliseconds means that the system can process input signals and generate outputs very quickly. Shorter delay time can reduce the time difference between signal acquisition and warning signal issuance, reduce the risk of signal loss or delay due to processing delays, improve the system's ability to capture and process signals, and enhance the reliability of the system.

[0065] Support Vector Machine (SVM): Support vector machine is a machine learning algorithm that is particularly suitable for classification and regression problems. In the intelligent analysis unit, SVM is used to perform real-time analysis and anomaly detection on signals. It can identify patterns, trends and categories in signals and determine whether the signal is normal based on these features.

[0066] Pattern recognition: refers to the process of identifying specific patterns or features from input signals, which can be used to identify the normal operating status and abnormal signal patterns of the device.

[0067] Trend analysis: refers to the process of predicting the future direction of input signals through time series analysis, which helps to promptly detect potential problems in the signals, including device performance degradation and fault warnings.

[0068] Signal classification: refers to the process of classifying input signals into different categories or types. It can be used to distinguish different types of signals, including normal signals, abnormal signals, and noise signals.

[0069] Pattern anomaly detection: refers to the process of identifying signals that deviate significantly from the normal pattern, which can promptly detect abnormal signals that do not conform to the normal pattern.

[0070] Trend anomaly detection: refers to the process of identifying signals that deviate significantly from the expected trend. It can predict the future direction of the signal and detect potential anomalies in a timely manner.

[0071] Signal anomaly identification: refers to the process of further analyzing abnormal signals to determine the type and cause of the anomaly, which can provide information for subsequent troubleshooting and maintenance decisions.

[0072] Sound alarm: refers to the process of alerting users by issuing specific sound signals.

[0073] Visual Alert: Refers to the process of alerting users by displaying specific visual signals (indicator lights, screen displays).

[0074] Vibration Alert: refers to the process of alerting users by emitting vibration signals.

[0075] Abnormal type: refers to the result of classifying abnormal signals, including device failure, intrusion detection, and performance degradation. Understanding the abnormal type helps users quickly determine the nature and severity of the problem.

[0076] Abnormal location: refers to the specific location or area where the abnormal signal occurs, which helps users quickly locate the problem and take appropriate measures.

[0077] Exception severity: refers to the degree of impact of the abnormal signal on the system. Understanding the severity of the exception helps users judge the urgency and priority of the problem, so as to reasonably allocate resources for processing.

[0078] Recommended actions: refers to the processing suggestions or solutions provided to users based on the exception type, location and severity information, which can help users quickly solve the problem and restore the normal operation of the system.

[0079] 5. Analog signal simulation module The analog signal simulation module includes a scene generation unit, a signal generation unit and a simulation control unit; A scenario generating unit, used to generate a scenario of a simulation signal according to preset conditions, wherein the preset conditions include environmental parameters, event parameters, simulation requirements and technical parameters; A signal generation unit, used to generate a simulation signal according to the generated scenario, and simulate the signal characteristics in the real environment through a signal generation algorithm, wherein the signal generation algorithm includes a simulation algorithm based on a physical model, a generation algorithm based on data drive, a random signal generation algorithm, and a parameterized signal generation algorithm; The simulation control unit is used to control the generation process of the analog signal and supports the adjustment of signal parameters, including frequency, amplitude, phase, time delay, pulse width, duty cycle, noise level, harmonic distortion, modulation index and signal bandwidth.

[0080] It should be noted that environmental parameters include physical environment: temperature, humidity, air pressure, wind speed; geographical environment: topography, landform, building distribution; meteorological conditions: rainfall, haze, visibility.

[0081] Event parameters include event type: toxic agent leak, radiation leak, biological threat, fire, natural disaster, industrial accident; event intensity: leak rate, radiation intensity, virus concentration, fire size, earthquake intensity; event location: the specific location (coordinates, area) of the leak source or event; event time: the specific time or time range of the event.

[0082] Simulation requirements include simulation purpose: training, testing, evaluation, research; simulation accuracy: high fidelity, medium fidelity, low fidelity; simulation scope: local area, entire site, city scope; user needs: customized needs of specific users or organizations.

[0083] The technical parameters include sensor types: toxic agent concentration sensor, radiation intensity sensor, biological signal sensor, temperature sensor, humidity sensor, pressure sensor; data format: data format and transmission protocol of analog signals.

[0084] Simulation algorithm based on physical model: simulates the generation and propagation process of signals according to physical laws and principles, and is suitable for scenarios that require accurate simulation of signal characteristics.

[0085] Data-driven generation algorithm: Use existing data to generate simulated signals. By analyzing the statistical characteristics and rules of the data, simulated signals similar to real signals are generated. It is suitable for scenarios with abundant and easy-to-obtain data.

[0086] Random signal generation algorithm: Generates random signals based on probability distribution, which is suitable for simulating noise, interference and other signals with strong randomness.

[0087] Parameterized signal generation algorithm: allows users to adjust signal parameters according to needs, provides a flexible signal generation method, and is suitable for scenarios that require customized signal characteristics.

[0088] Frequency: refers to the number of times a signal vibrates per second, which determines the periodicity of the signal.

[0089] Amplitude: refers to the peak value or maximum value of the signal, reflecting the strength of the signal.

[0090] Phase: refers to the position of the signal waveform relative to a reference point, which determines the phase relationship of the signal.

[0091] Time delay: refers to the time required for a signal to propagate from its generation to its reception point.

[0092] Pulse width: refers to the duration of a pulse signal, which is an important characteristic of a pulse signal.

[0093] Duty cycle: refers to the proportion of high level in the pulse signal, which has an important influence on the characteristics and application of the pulse signal.

[0094] Noise level: refers to the intensity of random noise mixed in the signal, which affects the clarity and accuracy of the signal.

[0095] Harmonic distortion: refers to the ratio of harmonic components to fundamental components in a signal, reflecting the degree of distortion of the signal.

[0096] Modulation Index: refers to the ratio of the amplitude of the modulating signal to the amplitude of the carrier signal.

[0097] Signal bandwidth: refers to the frequency range occupied by the signal, which determines the signal's transmission capacity and anti-interference ability.

[0098] 6. Intelligent diagnosis and maintenance module The intelligent diagnosis and maintenance module includes a status monitoring unit, a fault diagnosis unit and a maintenance reminder unit; The status monitoring unit is used to monitor the system operation status in real time. By collecting the parameters of the device during operation, the system health status is evaluated in real time, and the monitoring data is transmitted to the fault diagnosis unit for analysis in real time. The parameters include the device temperature, current, voltage, operation time, and sensor status; The fault diagnosis unit models the operating status of the device through a long short-term memory network, identifies abnormal modes in the operation of the device, and implements fault diagnosis, which includes determining the fault type, fault location, and severity; The maintenance reminder unit is used to generate maintenance suggestions based on the diagnosis results and display the device health status and maintenance suggestions through the user interface. The maintenance suggestions include maintenance steps, required tools and precautions.

[0099] It should be noted that the status monitoring unit collects operating parameters through the sensor network deployed on the device. The sensors include temperature sensors, current sensors, and voltage sensors, which can obtain the operating status data of the device in real time. In order to ensure real-time performance, the status monitoring unit collects data twice per second to ensure that slight changes in the device status can be captured in a timely manner.

[0100] Long Short-Term Memory Network (LSTM): is a special type of recurrent neural network, specifically designed to solve the gradient vanishing and gradient exploding problems of traditional RNN when processing long sequence data. LSTM can effectively capture long-term dependencies in time series data by introducing a "gate" mechanism.

[0101] LSTM modeling: The extracted feature sequence is input into the LSTM network, and a model of the device operation status is established by learning the patterns in the time series data. The specific steps are as follows: 1. Input sequence: Take the time series data as input and input it into the LSTM network.

[0102] 2. Hidden state update: LSTM updates the hidden state through the synergy of the input gate, forget gate, and output gate.

[0103] 3. Output prediction: The output layer of LSTM predicts the operating status of the device based on the hidden state to determine whether there is an abnormality.

[0104] Determine the fault type including: Overheat fault: If the temperature change rate exceeds the set threshold (increase of 5°C per second), or the temperature peak exceeds the normal range (exceeding 55°C), it is judged as an overheat fault.

[0105] Cooling system failure: If the temperature fluctuation range increases abnormally (more than 20°C) and the temperature continues to rise, it is a cooling system failure.

[0106] Short circuit fault: If the current change rate increases sharply (increases by 2A per second), or the current peak exceeds the normal range (exceeds 3A), it is judged as a short circuit fault.

[0107] Power failure: If the current fluctuation range increases abnormally (exceeds 1A) and the current continues to decrease, it is a power failure.

[0108] Overvoltage fault: If the voltage change rate increases sharply (increases by 10V per second), or the voltage peak exceeds the normal range (exceeds 260V), it is judged as an overvoltage fault.

[0109] Low voltage fault: If the voltage change rate drops sharply (10V per second), or the voltage peak is lower than the normal range (lower than 200V), it is judged as a low voltage fault.

[0110] Sensor failure: If the sensor status changes to "offline" or the abnormal rate of returned data exceeds the set threshold (more than 10%), it is judged as a sensor failure.

[0111] Determining the fault location includes: Local overheating: If a temperature sensor at a specific location detects an abnormally high temperature and the surrounding sensors do not detect similar abnormalities, the fault location is determined to be near the sensor.

[0112] Overall overheating: If temperature sensors in multiple locations detect abnormally high temperatures, the fault may be in the overall cooling system of the device.

[0113] Local short circuit: If a current sensor at a specific location detects an abnormally high current and the surrounding sensors do not detect similar abnormalities, the fault location is judged to be near the sensor.

[0114] Overall power failure: If current sensors in multiple locations detect abnormally low current, the fault may be in the overall power system of the device.

[0115] Local voltage is too high: If a voltage sensor at a specific location detects an abnormally high voltage and the surrounding sensors do not detect similar abnormalities, the fault location is judged to be near the sensor.

[0116] The overall voltage is too low: If voltage sensors in multiple locations detect abnormally low voltage, it is judged that the fault may be in the overall power supply system of the device.

[0117] Local sensor failure: If the status of a sensor at a specific location changes to "offline", the fault is determined to be located at that sensor.

[0118] Systematic sensor failure: If sensors in multiple locations are in abnormal status, the fault may be in the device's sensor network or data transmission system.

[0119] Determining severity includes: The severity of temperature anomalies includes minor faults: the temperature anomaly is small (exceeding the normal range by 5°C) and lasts for a short time (less than 1 minute); moderate faults: the temperature anomaly is moderate (exceeding the normal range by 10°C) and lasts for a long time (more than 5 minutes); severe faults: the temperature anomaly is large (exceeding the normal range by 20°C) and lasts for a long time (more than 10 minutes).

[0120] The severity of current anomalies includes: minor fault: the current anomaly amplitude is small (exceeding the normal range by 0.5A) and the duration is short (less than 1 minute); medium fault: the current anomaly amplitude is medium (exceeding the normal range by 1A) and the duration is long (exceeding 5 minutes); severe fault: the current anomaly amplitude is large (exceeding the normal range by 2A) and the duration is long (exceeding 10 minutes); The severity of voltage abnormalities includes minor faults: the voltage abnormality has a small amplitude (exceeding the normal range by 5V) and a short duration (less than 1 minute); moderate faults: the voltage abnormality has a moderate amplitude (exceeding the normal range by 10V) and a long duration (exceeding 5 minutes); severe faults: the voltage abnormality has a large amplitude (exceeding the normal range by 20V) and a long duration (exceeding 10 minutes).

[0121] The severity of sensor status abnormality includes minor faults: the sensor status abnormality rate is low (less than 5%), and the number of affected sensors is small (1-2); medium faults: the sensor status abnormality rate is medium (5%-10%), and the number of affected sensors is large (3-5); severe faults: the sensor status abnormality rate is high (more than 10%), and the number of affected sensors is large (more than 5).

[0122] The device health status is an important information displayed by the maintenance reminder unit, which is used to intuitively inform the user of the current operating status of the device. The health status includes the following aspects: The temperature status includes Normal: the device temperature is within the normal range (30°C to 50°C); Warning: the device temperature is close to the upper limit of the normal range (close to 55°C); Fault: the device temperature exceeds the normal range (over 60°C).

[0123] The current status includes normal: the device current is within the normal range (1A to 2A); warning: the device current is close to the upper limit of the normal range (close to 2.5A); fault: the device current exceeds the normal range (exceeds 3A).

[0124] The voltage status includes normal: the device voltage is within the normal range (220V to 240V); warning: the device voltage is close to the upper or lower limit of the normal range (close to 210V or 250V); fault: the device voltage exceeds the normal range (lower than 200V or higher than 260V).

[0125] The operating time status includes normal: the device operating time is within the expected range (8 hours per day); warning: the device operating time is close to the expected upper limit (more than 10 hours); fault: the device operating time exceeds the expected upper limit (more than 12 hours).

[0126] The sensor status includes normal: all sensors are online and return valid data; warning: some sensors are abnormal (data abnormality rate exceeds 5%); fault: the sensor is offline or the data abnormality rate exceeds 10%.

[0127] The maintenance reminder unit will also provide matters that need to be paid attention to during maintenance to ensure the safety and effectiveness of maintenance. The following are common matters that need to be paid attention to: Maintenance steps include the following: Overheating failure: Check whether the device cooling system is working properly; clean the device radiator or cooling fan; check whether there are obstacles around the device that hinder heat dissipation.

[0128] Short circuit failure: Check whether the power cord and connection points of the device are damaged; check whether there is a short circuit inside the device; replace damaged fuses or circuit protection devices.

[0129] Voltage is too high or too low: Check whether the power supply of the device is normal; check whether the power cord is damaged or has poor contact; adjust the power supply voltage of the device to the normal range.

[0130] Sensor failure: Check whether the sensor is online and reconnect the sensor; check whether the sensor is damaged and replace it if necessary; calibrate the sensor to ensure that the data it returns is accurate.

[0131] Fault of excessive running time: Check whether the device has been running continuously for a long time, and run it intermittently if necessary; check whether the device requires maintenance or servicing; check whether the device has any fault that causes abnormally extended running time.

[0132] The tools required include the following: General tools: screwdrivers (Phillips and flat head), wrenches, multimeter, pliers.

[0133] Electrical tools: voltmeter, ammeter, insulating tape, wire strippers.

[0134] Cooling system tools: cleaning brush, heat gun, coolant.

[0135] Sensor tools: calibration devices, sensor testers, sensor installation tools.

[0136] Other tools: anti-static wrist strap, protective gloves, safety glasses.

[0137] Things to note include the following: Safety precautions: Before performing any maintenance operation, make sure the device is powered off; wear appropriate protective equipment, such as gloves and safety glasses; ensure the working area is dry to avoid the risk of electric shock.

[0138] Operation precautions: When removing or installing parts, make sure to follow the correct order; when replacing parts, make sure the new parts are compatible with the original parts; when cleaning the device, avoid using overly wet cleaning tools to avoid damaging electronic components.

[0139] Environmental precautions; ensure that there is enough space around the device for maintenance operations; ensure that there are no flammable items around the device to avoid fire risks; after maintenance is completed, clean the work area and ensure that there are no tools or debris left behind.

[0140] The computer-based signal processing method in this embodiment includes the following steps: Step S1, collecting toxic agent concentration, radiation intensity, biological signals, temperature, humidity and pressure signals through a high-precision acquisition module.

[0141] It should be noted that the toxic agent concentration signal is collected by a high-sensitivity toxic agent concentration sensor to detect whether there are toxic gases or chemicals in the environment.

[0142] Radiation intensity signal: collected using radiation intensity sensors to monitor radiation levels in the environment, suitable for nuclear facilities and medical radiology scenarios.

[0143] Bio-signals: Collects bio-signals such as heart rate and respiratory rate, which are suitable for medical health monitoring and biological experiment scenarios.

[0144] Temperature signal: The temperature data of the environment or device is collected through the temperature sensor for environmental monitoring and industrial device operation status monitoring.

[0145] Humidity signal: Humidity sensors are used to collect ambient humidity, which is suitable for meteorological monitoring and warehouse environment control scenarios.

[0146] Pressure signal: pressure data is collected through pressure sensors for industrial pipeline pressure monitoring and meteorological air pressure monitoring Step S2, distributed signal collection is realized through a distributed processing module, and preliminary data processing is performed at the edge node using edge computing technology to reduce the amount of data transmission.

[0147] It should be noted that network connection: multiple sensor nodes are connected through wired (Ethernet, optical fiber) and wireless (Wi-Fi, 5G) networks to build a distributed signal acquisition network.

[0148] Edge computing: Perform preliminary data processing at edge nodes close to sensors to reduce data transmission volume and improve system efficiency.

[0149] Preliminary data processing includes data compression, data filtering, and data preprocessing. Data compression uses Huffman coding and wavelet transform algorithm to compress data to reduce storage and transmission costs; data filtering removes high-frequency noise through a low-pass filter to retain the main features of the signal; data preprocessing: normalize the collected signals to make them comparable in subsequent processing.

[0150] Step S3, fusing the collected signals of different types through a multi-signal fusion module, extracting key features and generating a comprehensive signal.

[0151] It should be noted that feature extraction: uses wavelet transform and Fourier transform algorithms to extract key features from different types of signals, including frequency features, time domain features and waveform features.

[0152] Fusion algorithm: weighted average, Bayesian fusion, and convolutional neural network algorithms are used to fuse the extracted features and generate a comprehensive signal.

[0153] Comprehensive signal: The fused signal can more comprehensively reflect the state of the environment or device. Through fusion processing, the characteristics of the signal can be enhanced and the analyzability of the signal can be improved.

[0154] Step S4, the real-time signal warning module performs real-time analysis on the fused signal, detects anomalies and issues warnings.

[0155] It should be noted that the early warning mechanism includes early warning signals: whether to issue an early warning signal is determined based on the analysis results, and the early warning signals include sound alarms, visual alarms and vibration alarms; alarm content: the alarm content includes the abnormality type, abnormality location, abnormality severity and recommended measures to help users respond quickly.

[0156] Step S5, generating a simulated signal by using a simulated signal simulation module to simulate a real environment, so as to test and verify the performance of the signal processing system.

[0157] It should be noted that the purpose of analog signal simulation is to test system performance: to simulate the real environment by generating analog signals and test the performance of the signal processing system; to verify system reliability: to ensure that the system can operate stably in various complex environments.

[0158] Step S6, monitor the system operation status and diagnose faults through the intelligent diagnosis and maintenance module, generate maintenance suggestions and remind users.

[0159] It should be noted that the diagnostic method of fault diagnosis is: using long short-term memory network to model the operating status of the device and identify abnormal patterns; diagnostic results: determine the fault type, fault location and severity.

[0160] Maintenance recommendations: Generate maintenance recommendations based on diagnostic results, including maintenance steps, required tools and precautions; Reminder method: Display device health status and maintenance recommendations through the user interface, and support SMS, email and other methods to remind users.

[0161] The computer-based signal processing device in this embodiment includes: A multi-sensor interface is used to connect a toxic agent concentration sensor, a radiation intensity sensor, a biological signal sensor, a temperature sensor, a humidity sensor and a pressure sensor, and the multi-sensor interface supports multiple sensor types and communication protocols.

[0162] It should be noted that the reasons for the multi-sensor interface design include versatility: the ability to connect multiple sensors to achieve multi-parameter monitoring and be suitable for complex environments; compatibility: support for multiple communication protocols to ensure compatibility with sensors from different manufacturers and types, communication protocols include SPI, I2C, and UART.

[0163] The input interface is used to connect to a sensor and receive a signal. The input interface supports multiple sensor interface standards, including SPI, I2C, and UART.

[0164] It should be noted that the reasons for the input interface design include versatility: supporting multiple interface standards to ensure that the device can be connected to various sensors; flexibility: being able to receive different types of signals and being suitable for a variety of application scenarios.

[0165] The network interface is used to realize real-time transmission and distributed processing of data, and the network interface supports Ethernet and Wi-Fi communications.

[0166] It should be noted that the reasons for the network interface design include efficient transmission: supporting high-speed communication protocols to ensure the real-time and reliability of data transmission; distributed processing: supporting distributed processing architecture to improve the system's processing capabilities and efficiency.

[0167] A processor, used to execute the signal processing method, wherein the processor is a multi-core processor and supports parallel processing; It should be noted that the reasons for processor design include high performance: multi-core processors can handle large amounts of data and meet the needs of complex signal processing; parallel processing: support parallel processing to improve the processing speed and efficiency of the system.

[0168] The memory is used to store the collected signals, processing results and models, and the memory includes 16GB of RAM and a 512GB solid-state hard disk.

[0169] It should be noted that the reasons for memory design include large-capacity storage: meeting the needs of large-scale data storage and ensuring data integrity and availability; efficient reading and writing: solid-state drives have fast reading and writing capabilities, improving the overall performance of the system.

[0170] The output interface is used to output processing results and warning information. The output interface supports multiple display and communication interfaces, including HDMI, USB and Ethernet.

[0171] It should be noted that the reasons for the output interface design include versatility: supporting multiple interfaces to ensure that the device can be connected to various devices; flexibility: being able to meet the needs of different users and providing multiple output methods.

[0172] A user interface is used to display signal processing results, warning information and device status, and the user interface supports touch screen operation and remote access.

[0173] It should be noted that the reasons for user interface design include user-friendliness: providing an intuitive user interface to facilitate user operation and monitoring; remote monitoring: supporting remote access to improve the flexibility and practicality of the system.

[0174] The display module is used to display the signal processing results and system status. The display module is a high-resolution LCD display screen.

[0175] It should be noted that the reasons for the display module design include clear display: high-resolution display screen can clearly display complex processing results and system status; high-quality visual effects: support high-quality display technology and enhance user experience.

[0176] A communication module is used to realize distributed transmission and processing of signals, and the communication module supports wired and wireless communication protocols, including Ethernet, Wi-Fi and 5G.

[0177] It should be noted that the reasons for the design of the communication module include efficient transmission: supporting multiple communication protocols to ensure the efficiency and reliability of data transmission; distributed processing: supporting distributed processing to improve the flexibility and scalability of the system.

[0178] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A computer-based signal processing system, characterized in that include: High-precision acquisition module, which collects signals through sensors and analog-to-digital converters; Distributed processing module, which realizes distributed signal collection and processing through network connection and edge computing technology; Multi-signal fusion module, which performs fusion processing on collected signals of different types through feature extraction and fusion algorithm; The real-time signal warning module uses support vector machines to analyze signals in real time, thus achieving real-time monitoring and warning of abnormal signals; Analog signal simulation module, which generates analog signals through computer simulation technology to simulate the real environment; The intelligent diagnosis and maintenance module monitors the system operation status and diagnoses faults through long short-term memory networks, and provides maintenance reminders.

2. The computer-based signal processing system of claim 1, wherein: The high-precision acquisition module includes: The signal collection unit includes a toxic agent concentration sensor, a radiation intensity sensor, a biological signal sensor, a temperature sensor, a humidity sensor, and a pressure sensor, which are used to collect signals. The response time of the collection is no more than 1 second and the error is less than 1%; An analog-to-digital conversion unit, comprising an analog-to-digital converter, for converting the collected analog signal into a digital signal, wherein the analog-to-digital converter has a 16-bit resolution and a sampling rate of 100 kHz; The signal conditioning unit includes a filtering circuit and an amplifying circuit, which are used to filter, amplify and normalize the collected signal. The filtering circuit adopts a low-pass filter with a cut-off frequency of 10 Hz, and the gain range of the amplifying circuit is 1-100 times.

3. The computer-based signal processing system of claim 1, wherein: The distributed processing module includes: A network connection unit connects the sensor and the real-time signal processing unit through wired and wireless networks to build a distributed signal processing network. The wired network includes Ethernet, fiber optic communication, industrial bus and serial communication. The wireless network includes Wi-Fi, 5G, ZigBee, Bluetooth, LoRa and NB-IoT. A data transmission unit, which is used to realize signal transmission and supports data compression, data encryption and data verification functions. The transmission rate is higher than 100Mbps. The data compression includes Huffman coding, wavelet transform and discrete cosine transform DCT. The data encryption includes advanced encryption standard AES, asymmetric encryption algorithm RSA and elliptic curve encryption algorithm ECC. The data verification includes cyclic redundancy check CRC, CRC32 and parity check. The distributed computing unit is used to realize the distributed processing of signals. The distributed processing includes performing preliminary data processing at the edge node through edge computing technology to reduce the amount of data transmission, and then uploading the processed results. The preliminary data processing includes data preprocessing, feature extraction and simple analysis.

4. The computer-based signal processing system of claim 1, wherein: The multi-signal fusion module comprises: A feature extraction unit, which uses wavelet transform and Fourier transform algorithms to extract key features from the collected signal, wherein the key features include frequency features, time domain features and waveform features; A fusion processing unit, which performs fusion processing on the extracted features through a fusion algorithm to achieve signal fusion, wherein the fusion algorithm includes weighted average, Bayesian fusion and convolutional neural network; A fusion algorithm selection unit selects a fusion algorithm based on a signal type, wherein the signal type includes a toxic agent concentration signal, a radiation intensity signal, a biological signal, a temperature signal, a humidity signal, and a pressure signal.

5. The computer-based signal processing system of claim 1, wherein: The real-time signal warning module includes: Real-time signal processing unit, used to process the collected signals in real time, using FPGA to accelerate the signal processing process and achieve signal processing with a delay of less than 10 milliseconds; An intelligent analysis unit, which uses a support vector machine to perform real-time analysis and anomaly detection on signals, wherein the real-time analysis includes pattern recognition, trend analysis and signal classification, and the anomaly detection includes pattern anomaly detection, trend anomaly detection and signal anomaly recognition; The early warning decision unit determines whether to issue an early warning signal based on the analysis results. The early warning signal includes the alarm type and alarm content. The alarm type includes sound alarm, visual alarm and vibration alarm. The alarm content includes the abnormality type, abnormality location, abnormality severity and recommended measures.

6. The computer-based signal processing system of claim 1, wherein: The analog signal simulation module comprises: A scene generation unit, used to generate a scene of a simulation signal according to preset conditions, wherein the preset conditions include environmental parameters, event parameters, simulation requirements and technical parameters; A signal generation unit, used to generate a simulation signal according to the generated scenario, and simulate the signal characteristics in the real environment through a signal generation algorithm, wherein the signal generation algorithm includes a simulation algorithm based on a physical model, a generation algorithm based on data drive, a random signal generation algorithm, and a parameterized signal generation algorithm; The simulation control unit is used to control the generation process of the analog signal and supports adjustment of signal parameters, including frequency, amplitude, phase, time delay, pulse width, duty cycle, noise level, harmonic distortion, modulation index and signal bandwidth.

7. The computer-based signal processing system of claim 1, wherein: The intelligent diagnosis and maintenance module includes: The status monitoring unit is used to monitor the system operation status in real time, evaluate the system health status in real time by collecting the parameters of the device during operation, and transmit the monitoring data to the fault diagnosis unit for analysis in real time. The parameters include the temperature, current, voltage, operation time and sensor status of the device; A fault diagnosis unit, which models the operating status of the device through a long short-term memory network, identifies abnormal modes in the operation of the device, and implements fault diagnosis, wherein the fault diagnosis includes determining the fault type, fault location, and severity; The maintenance reminder unit is used to generate maintenance suggestions based on the diagnosis results and display the device health status and maintenance suggestions through the user interface. The maintenance suggestions include maintenance steps, required tools and precautions.

8. A computer-based signal processing method, characterized in that The following steps are involved: Step S1, collecting toxicant concentration, radiation intensity, biological signals, temperature, humidity and pressure signals through a high-precision acquisition module; Step S2, realizing distributed signal collection through a distributed processing module, and performing preliminary data processing at edge nodes using edge computing technology to reduce data transmission volume; Step S3, fusing the collected signals of different types through a multi-signal fusion module, extracting key features and generating a comprehensive signal; Step S4, using a real-time signal warning module to analyze the fused signal in real time, detect anomalies and issue a warning; Step S5, generating a simulated signal by a simulated signal simulation module to simulate a real environment, so as to test and verify the performance of the signal processing system; Step S6, monitor the system operation status and diagnose faults through the intelligent diagnosis and maintenance module, generate maintenance suggestions and remind users.

9. A computer-based signal processing device, characterized in that include: A multi-sensor interface, used to connect a toxic agent concentration sensor, a radiation intensity sensor, a biological signal sensor, a temperature sensor, a humidity sensor, and a pressure sensor, wherein the multi-sensor interface supports multiple sensor types and communication protocols; An input interface, used to connect a sensor and receive a signal, wherein the input interface supports a variety of sensor interface standards, including SPI, I2C, and UART; A network interface, used to realize real-time transmission and distributed processing of data, the network interface supports Ethernet and Wi-Fi communications; A processor, used to execute the signal processing method, wherein the processor is a multi-core processor and supports parallel processing; A memory, used to store the collected signals, processing results and models, the memory including 16GB of RAM and a 512GB solid-state hard disk; An output interface, used to output processing results and warning information, the output interface supports a variety of display and communication interfaces, including HDMI, USB and Ethernet; A user interface, used to display signal processing results, warning information and device status, wherein the user interface supports touch screen operation and remote access; A display module, used to display signal processing results and system status, wherein the display module is an LCD display screen; A communication module is used to realize distributed transmission and processing of signals, and the communication module supports wired and wireless communication protocols, including Ethernet, Wi-Fi and 5G.

Images