Low-power-consumption signal detection method and system in metal card production process

Abstract

The invention provides a low-power-consumption signal detection method and system in a metal card production process, and the method comprises the following steps: obtaining signal data in the metal card production process, and encrypting the signal data through a quantum encryption technology. Through innovative technologies such as quantum encryption signal acquisition, feature extraction combining artificial intelligence and a quantum algorithm, quantum state signal feature modeling and the like, the accuracy of signal detection is greatly improved, various tiny defects in the metal card production process can be accurately recognized, and the product quality is effectively improved; through combination of an energy recovery technology and dynamic power supply management, the power consumption of detection equipment is remarkably reduced while the detection function is guaranteed, the production cost is greatly reduced, and the energy-saving and environment-friendly development trend is met; through the quantum encryption technology and adaptive filtering based on the block chain, the security and anti-interference capability in the signal acquisition, transmission and processing process are ensured, and stable operation in a complex metal card production environment can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of metal card production, and in particular to a low-power consumption signal detection method and system in a metal card production process. Background Art

[0002] With the continuous development of smart card technology, metal cards have gained widespread application in finance, access control, and identity verification due to their unique appearance, excellent durability, and high security. During the production of metal cards, precise detection of various signals is required to ensure product quality. For example, during the packaging of metal card chips, welding signals must be detected to ensure the reliability of the connection between the chip and the metal card substrate. During the surface treatment of metal cards, electromagnetic signals must be detected to monitor the accuracy of the treatment process. However, traditional signal detection methods have many problems in metal card production.

[0003] On the one hand, due to the complex production environment of metal cards and the presence of a large amount of electromagnetic interference, traditional detection methods have poor anti-interference capabilities, resulting in inaccurate test results and affecting product quality; On the other hand, traditional testing equipment usually consumes a lot of power, which not only increases production costs but also does not conform to the current development trend of energy conservation and environmental protection; In addition, in some production scenarios with limited energy supply, especially in the large-scale production of metal cards, the energy consumption and cost increase caused by high power consumption are particularly prominent and cannot meet production needs; Therefore, a low-power signal detection method and system in the metal card production process are proposed. Summary of the Invention

[0004] In view of this, the embodiments of the present invention hope to provide a low-power signal detection method and system in the metal card production process to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0005] To solve the above technical problems, a technical solution adopted in this application is a low-power signal detection method in the metal card production process, comprising the following steps: Step 1: Obtain signal data during the metal card production process and encrypt the signal data using quantum encryption technology; Step 2: Filter the signal data using an adaptive filtering algorithm based on blockchain technology; Step 3: A low-noise amplifier made of nanomaterials automatically adjusts the gain based on the initial strength of the signal data through a smart contract to amplify the filtered signal data; Step 4: Using a combination of artificial intelligence algorithms and quantum algorithms, extract features from the amplified signal data to obtain a data feature set; Step 5: Based on the data feature set, use quantum bits to build a signal feature model and train the signal feature model; Step 6: Based on the established signal feature model, a pattern matching algorithm of quantum key encryption is used to detect signal data and generate detection results.

[0006] As a further preferred embodiment of the present technical solution, in step 2, the method for filtering the signal data includes the following steps: Step 201: Import the received signal data into the blockchain-based filtering system, and record the initial information of the signal data into the blockchain distributed ledger; Step 202: Analyze the signal data using time domain analysis, frequency domain analysis, or time-frequency analysis to identify the type and characteristics of interference in the signal data. Step 203: The adaptive filtering algorithm automatically adjusts the filter parameters according to the interference type and characteristics present in the signal data; Step 204: Filter the signal data based on the filter with adjusted parameters to remove interference signals, and record the filtering process and results on the blockchain.

[0007] As a further preferred embodiment of the present technical solution, in step 4, the artificial intelligence algorithm is a convolutional neural network, and the quantum algorithm is a quantum annealing algorithm; The method for obtaining the data feature set comprises the following steps: Step 401: converting the amplified signal data into a two-dimensional matrix form suitable for convolutional neural network input; Step 402: Using the convolutional layer and pooling layer of the convolutional neural network to extract features from the signal data to obtain a preliminary feature vector; Step 403: The preliminary feature vector is used as input to the quantum annealing algorithm. The quantum annealing algorithm optimizes and combines the features through quantum bit encoding and quantum gate operations to obtain a data feature set.

[0008] As a further preferred embodiment of the present technical solution, in step 5, when constructing the signal characteristic model using quantum bits, a quantum gate circuit is used to construct the signal characteristic model, and the quantum gate circuit includes a single quantum bit gate and a multi-qubit gate; The method for constructing a signal feature model comprises the following steps: Step 501: Determine the number and initial state of quantum bits based on the dimension of the data feature set and the correlation between the features; Step 502: Using quantum gate circuits to operate on quantum bits, simulate the nonlinear relationship between signal data features, and construct a signal feature model; Step 503: Acquire known signal data samples and use the known signal data samples to train the signal feature model; the known signal data samples match the data feature set in terms of data type and feature dimension.

[0009] As a further preferred embodiment of the present technical solution, in step six, the quantum key encryption uses the E91 quantum key distribution protocol to generate an encryption key, and encrypts the data features and the standard features in the signal feature model; when the pattern matching algorithm using quantum key encryption performs pattern matching, the cosine similarity between the encrypted feature vectors is calculated. If the similarity is greater than a preset similarity threshold, the signal data is determined to be normal; if the similarity is less than the preset similarity threshold, the signal data is determined to be abnormal. At the same time, the system automatically triggers an early warning mechanism and records the abnormal signal data information to the blockchain distributed ledger.

[0010] As a further preferred embodiment of the present technical solution, in step three, the low-noise amplifier made of the nanomaterial is a carbon nanotube field-effect transistor amplifier; the smart contract compares the initial intensity of the signal data with a preset intensity threshold range; if the initial intensity is lower than the first threshold, the gain is increased to the first gain level; if the initial intensity is between the first threshold and the second threshold, the gain is set to the second gain level; if the initial intensity is higher than the second threshold, the gain is decreased to the third gain level.

[0011] As a further preferred embodiment of the present technical solution, in step 1, the signal data is acquired by collecting multi-dimensional signals of the metal card production equipment through a quantum sensor, wherein the quantum sensor is a sensor based on a superconducting quantum interference device, and the multi-dimensional signals of the metal card production equipment include current signals, voltage signals, and magnetic field signals; The quantum encryption technology adopts the BB84 protocol in the quantum key distribution protocol. The communicating parties generate a shared encryption key through the polarization state of a single photon and perform a one-time encryption operation on the signal data.

[0012] To solve the above technical problems, another technical solution adopted by this application is: a low-power signal detection system in the metal card production process, the system comprising: a signal acquisition and encryption module, a blockchain filtering module, a low-noise amplification module, a feature extraction module, a model building and training module, and a signal detection module; The signal acquisition and encryption module is configured to obtain signal data during the metal card production process and encrypt the signal data using quantum encryption technology; The blockchain filtering module is configured to filter the signal data using an adaptive filtering algorithm based on blockchain technology; The low-noise amplification module is configured as a low-noise amplifier made of nanomaterials, which automatically adjusts the gain through smart contracts according to the initial strength of the signal data to amplify the filtered signal data; The feature extraction module is configured to extract features from the amplified signal data using a combination of artificial intelligence algorithms and quantum algorithms to obtain a data feature set; The model building and training module is configured to build a signal feature model using quantum bits based on the data feature set and train the signal feature model; The signal detection module is configured to perform signal data detection based on the established signal feature model and adopt a pattern matching algorithm of quantum key encryption to generate a detection result.

[0013] As a further preferred embodiment of the present technical solution, the system also includes an energy management module, which is configured to use energy recovery technology to collect waste energy in the production environment and convert it into electrical energy storage, and combine it with dynamic power management technology to automatically reduce the operating frequency and voltage of the equipment to enter a low-power standby mode when there is no signal data processing.

[0014] As a further preferred embodiment of the present technical solution, data interaction is performed between the signal acquisition and encryption module, the blockchain filtering module, the low-noise amplification module, the feature extraction module, the model building and training module, and the signal detection module through an internal data interface.

[0015] The embodiment of the present invention adopts the above technical solution, which has the following advantages: 1. This invention significantly improves the accuracy of signal detection through innovative technologies such as quantum encryption signal acquisition, feature extraction combining artificial intelligence and quantum algorithms, and quantum state signal feature modeling. It can accurately identify various subtle defects in the metal card production process, effectively improving product quality. 2. The present invention combines energy recovery technology with dynamic power management, significantly reducing the power consumption of detection equipment while ensuring detection functions, greatly reducing production costs, and conforming to the development trend of energy conservation and environmental protection; 3. This invention uses quantum encryption technology and blockchain-based adaptive filtering to ensure security and anti-interference capabilities during signal acquisition, transmission, and processing, and can operate stably in complex metal card production environments. 4. The present invention uses a signal feature model constructed through quantum bits and the application of quantum algorithms in feature extraction, so that the system has efficient learning and recognition capabilities and can quickly adapt to different production processes and signal detection requirements.

[0016] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of a low-power signal detection method in a metal card production process according to the present invention; Figure 2 Schematic diagram of the flow of the signal data filtering processing method of the present invention; Figure 3 Schematic diagram of the process of obtaining a data feature set according to the present invention; Figure 4 A flow chart of the method for constructing a signal feature model according to the present invention; Figure 5 This is a schematic diagram of the functional modules of a low-power signal detection system in the metal card production process of the present invention. DETAILED DESCRIPTION

[0019] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0020] It should be clear that the following embodiments of the present disclosure are described through specific concrete examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0021] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this disclosure, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0022] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The illustrations only show components related to the present disclosure and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0023] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples. However, one skilled in the art will appreciate that the aspects described can be practiced without these specific details.

[0024] Figure 1 This is a flow chart of a low-power signal detection method in a metal card production process according to an embodiment of the present invention. It should be noted that if there are substantially the same results, the method of this application is not based on Figure 1 The process sequence shown is limited. Figures 1-4 As shown: A low-power signal detection method in the metal card production process includes the following steps: Step 1: Obtain signal data during the metal card production process and encrypt the signal data using quantum encryption technology; The specific implementation method for obtaining signal data during the metal card production process is as follows: First, a quantum sensor based on a superconducting quantum interference device (SQUID) is selected. For example, during the chip embedding process, it can sensitively capture the extremely weak current changes generated at the moment the chip is connected to the metal card substrate, as well as the subtle magnetic field fluctuations generated by the operation of the surrounding equipment.

[0025] Then, the multi-dimensional signals of the metal card production equipment are comprehensively collected; on the production line, high-precision current transformers are connected in series in the power supply lines of key equipment to monitor the current signals in real time. The range can be set according to the operating current range of the equipment, such as 0-10A, with an accuracy of up to milliampere level; voltage sensors are installed at the power access end and key circuit nodes of the equipment to monitor the voltage signal, with a range of 0-380V and an accuracy of 0.1V; with the help of superconducting quantum interferometer sensors arranged around the equipment, the magnetic field signals around the equipment are captured, and the measurement accuracy can reach the nanotesla level.

[0026] The specific implementation method of encrypting signal data using quantum encryption technology is as follows: First, the BB84 quantum key distribution protocol is used. At the signal acquisition end, single photons are randomly generated and assigned different polarization states, such as horizontal, vertical, +45°, and -45°, to encode signal data. For example, a binary "0" is encoded as a horizontally polarized photon, and a "1" is encoded as a vertically polarized photon. The receiving end then randomly selects a measurement basis (such as a horizontal-vertical measurement basis or a +45°-45° measurement basis) to measure the received single photon. The communicating parties compare their respective measurement bases through a classical communication channel (such as a wired network) and only retain the measurement results with consistent measurement bases as the shared key. During this process, the noise and interference of the quantum channel are continuously monitored. If the noise exceeds a threshold, the key is redistributed. Finally, the generated shared key is used to encrypt the collected signal data in a one-time-one-pad manner; for example, the signal data is divided into bytes, and each byte is XORed with the corresponding key byte to obtain the encrypted signal data, ensuring the security of the data during transmission.

[0027] Step 2: Filter the signal data using an adaptive filtering algorithm based on blockchain technology; Specifically, the collected and encrypted signal data is first transmitted to the blockchain-based filtering system. In the system, the initial information of the signal data, such as the acquisition time (accurate to the millisecond), the acquisition location (corresponding to the specific station number on the production line), and the initial signal strength, are all recorded in the blockchain distributed ledger. For example, if the signal was collected at 14:23:15 on May 10, 2025, at station No. 15 on production line No. 3, with an initial current strength of 3.5A, this information will be accurately recorded on the blockchain. Then, use time domain analysis to observe how the signal changes over time, such as the rising and falling edge times of the current signal and the fluctuation period of the voltage signal. Use frequency domain analysis to convert the signal from the time domain to the frequency domain through Fourier transform, analyze its frequency components, and determine the main interference frequency. Or use time-frequency analysis, such as wavelet transform, to simultaneously obtain the characteristics of the signal at different times and frequencies. For example, analysis reveals the presence of 60Hz power frequency interference (caused by the mains) and some high-frequency pulse interference (caused by the instantaneous switching action of the equipment). Next, based on the analysis results, accurately identify the interference type and characteristics. For 60Hz power frequency interference, determine its amplitude and phase; for high-frequency pulse interference, determine its pulse width, occurrence frequency, peak intensity and other characteristics. Subsequently, the adaptive filtering algorithm automatically adjusts the filter parameters based on the identified interference type and characteristics. For 60Hz power frequency interference, the filter cutoff frequency is adjusted to between 59Hz and 61Hz to enhance the ability to suppress interference of this frequency. For high-frequency pulse interference, the filter bandwidth and gain are adjusted to enable the filter to effectively filter out this type of interference. Finally, the signal data is filtered based on the filter with adjusted parameters to remove interference signals. The filtered signal data, such as the current signal, becomes smoother and no longer contains obvious 60Hz power frequency interference and high-frequency pulse interference. At the same time, the filtering process (including the analysis method used and the adjusted parameter values) and results (such as the intensity and frequency distribution of the filtered signal) are recorded on the blockchain for subsequent tracing and analysis.

[0028] Step 3: A low-noise amplifier made of nanomaterials automatically adjusts the gain based on the initial strength of the signal data through a smart contract to amplify the filtered signal data; Step 4: Using a combination of artificial intelligence algorithms and quantum algorithms, extract features from the amplified signal data to obtain a data feature set; Specifically, first, the amplified signal data is converted into a two-dimensional matrix form suitable for convolutional neural network input; for example, the continuous current signal is divided into multiple time segments in chronological order, each segment contains 100 sampling points, and the data of these sampling points form a row of the matrix. The data of multiple time segments form a complete two-dimensional matrix; Then, the convolutional layer and pooling layer of the convolutional neural network are used to extract features from the signal data. The convolutional layer slides different convolution kernels (such as 3×3 or 5×5 convolution kernels) on the signal data matrix to extract local features of the signal, such as edge features and frequency change features, and generate multiple feature maps. The pooling layer performs dimensionality reduction on the feature map, for example, using a 2×2 maximum pooling window to retain the main features in the feature map, reduce the amount of data, and obtain a preliminary feature vector. Finally, the preliminary feature vector is used as the input of the quantum annealing algorithm, which optimizes the combination of features through quantum bit encoding and quantum gate operations. Quantum bit encoding encodes the information in the preliminary feature vector into the state of the quantum bit, and rotates and entangles the quantum bit through quantum gate operations (such as Hadamard gate and Pauli gate) to remove redundant features and obtain a data feature set. For example, after being processed by the quantum annealing algorithm, the data feature set is more compact and can more accurately reflect the essential characteristics of the signal.

[0029] Step 5: Based on the data feature set, use quantum bits to build a signal feature model and train the signal feature model; Specifically, first, the number and initial state of qubits are determined based on the dimension of the data feature set and the correlation between the features. Assuming the dimension of the data feature set is 150, after analyzing the correlation between the features, it is determined that 80 qubits are used to build the model. By calculating the degree of correlation between the features, the initial state of each qubit is determined. For example, some qubits are initially in the |0> state and some are in the |1> state. Then, quantum gate circuits containing single-qubit gates and multi-qubit gates are used to operate on qubits, simulating the nonlinear relationship between signal data features and building a signal feature model. For example, multi-qubit gate operations are used to entangle multiple qubits and simulate the complex interaction between signal features. Finally, known signal data samples are obtained and used to train the signal feature model. The known signal data samples match the data feature set in terms of data type and feature dimension. For example, 2,000 sets of known normal and abnormal signal data samples are selected from a large amount of past production data. These samples contain the same signal features such as current, voltage, and magnetic field as the current data feature set. During the training process, the parameters of the quantum gate circuit are continuously adjusted to make the model output close to the features of the known samples, thereby improving the accuracy and generalization ability of the model.

[0030] Step 6: Based on the established signal feature model, a pattern matching algorithm of quantum key encryption is used to detect signal data and generate a detection result; Specifically, first, the pattern matching algorithm of quantum key encryption uses the E91 quantum key distribution protocol to generate encryption keys; E91 protocol-related devices are deployed at the signal detection end and the reference model end respectively, and a shared encryption key is generated through the quantum channel; Then, the signal data features and the standard features in the signal feature model are encrypted; for example, each element in the signal data feature vector and the standard feature vector is XORed with the encryption key to obtain an encrypted feature vector; Finally, during pattern matching, the cosine similarity between the encrypted feature vectors is calculated; assuming the preset similarity threshold is 0.75; if the calculated cosine similarity is 0.8 (greater than the preset similarity threshold), the signal data is judged to be normal, indicating that the metal card production process is in a normal state; if the similarity is 0.7 (less than the preset similarity threshold), the signal data is judged to be abnormal, and the system automatically triggers an early warning mechanism, such as issuing an audible and visual alarm, and records the abnormal signal data information (including the time of occurrence of the abnormality, the characteristic value of the abnormal signal, the production process, etc.) to the blockchain distributed ledger, which facilitates subsequent analysis and tracing of the abnormal situation, timely adjustment of the production process, and ensures product quality.

[0031] In one embodiment, specifically, in step 2, the method for filtering the signal data includes the following steps: Step 201: Import the received signal data into the blockchain-based filtering system, and record the initial information of the signal data into the blockchain distributed ledger; Step 202: Analyze the signal data using time domain analysis, frequency domain analysis, or time-frequency analysis to identify the type and characteristics of interference in the signal data. Step 203: The adaptive filtering algorithm automatically adjusts the filter parameters according to the interference type and characteristics present in the signal data; Step 204: Filter the signal data based on the filter with adjusted parameters to remove interference signals, and record the filtering process and results on the blockchain; Specifically, for example, in a blockchain-based filtering system at a medium-sized metal card manufacturer, the signal acquisition device transmits the collected signal data to the filtering system through an encrypted channel. The system automatically imports the signal data and creates a new record in the blockchain distributed ledger, recording information such as the signal data acquisition time (e.g., 9:30:00 on June 1, 2025), the acquisition device number (e.g., S005), the signal type (current, voltage, or magnetic field), and the initial intensity value (e.g., the initial current intensity is 2.8A). The system then uses a time-domain analysis algorithm to analyze the changes in the signal data along the time axis, determining characteristics such as the signal's fluctuation range and period. It then performs a frequency-domain analysis, converting the signal to the frequency domain through Fourier transform to identify the main frequency components in the signal, finding an interference frequency of 70 Hz. The system then uses a wavelet transform for time-frequency analysis to further clarify the distribution characteristics of the interference signal in time and frequency, determining that the interference type is periodic electromagnetic interference. Next, the adaptive filtering algorithm automatically adjusts the filter parameters based on the identified interference type and characteristics. For 70Hz periodic electromagnetic interference, the filter cutoff frequency is set to 68Hz-72Hz, the filter order is adjusted to enhance the ability to suppress interference at this frequency, and the filter coefficients are optimized to make it more adaptable to the signal characteristics. Finally, the signal data is filtered based on the filter with adjusted parameters to remove interference signals; the filtered signal data is recorded on the blockchain again, and the analysis method used in the filtering process, the adjusted parameter values, and the intensity and frequency distribution of the filtered signal and other detailed information are also recorded to provide data support for subsequent quality traceability and system optimization.

[0032] In one embodiment, specifically, in step 4, the artificial intelligence algorithm is a convolutional neural network, and the quantum algorithm is a quantum annealing algorithm; Among them, convolutional neural network is a deep learning model that is widely used in feature extraction and pattern recognition of image, speech, signal and other data. In this signal detection method, it is mainly used to perform preliminary feature extraction on the amplified signal data. Among them, the quantum annealing algorithm is an optimization algorithm based on the principles of quantum mechanics. In this signal detection scenario, it is used to further optimize and combine the preliminary feature vectors extracted by the convolutional neural network to obtain a more effective data feature set; By combining convolutional neural networks and quantum annealing algorithms, the convolutional neural network first performs preliminary feature extraction on the signal data, and then uses the quantum annealing algorithm to optimize and combine these features. This can more efficiently and accurately extract the key features of the signal data in the metal card production process, providing a high-quality data foundation for subsequent signal feature modeling and detection operations.

[0033] The method for obtaining a data feature set includes the following steps: Step 401: converting the amplified signal data into a two-dimensional matrix form suitable for convolutional neural network input; Step 402: Using the convolutional layer and pooling layer of the convolutional neural network to extract features from the signal data to obtain a preliminary feature vector; Step 403: The preliminary feature vector is used as input to the quantum annealing algorithm. The quantum annealing algorithm optimizes and combines the features through quantum bit encoding and quantum gate operations to obtain a data feature set. Specifically, for example, in the signal processing system of a metal card production workshop, the amplified current signal data length is 1000 sampling points. The system divides it into segments of 100 sampling points, resulting in a total of 10 segments. The data of these segments are rearranged to form a two-dimensional matrix with 10 rows and 100 columns. This matrix serves as the input data of the convolutional neural network. Then, the convolutional layer of the convolutional neural network uses a 3×3 convolution kernel to perform a convolution operation on the input two-dimensional matrix to extract local features of the signal, such as the mutation points and stable segments of the current signal, and generate multiple feature maps. The pooling layer uses a 2×2 maximum pooling window to reduce the dimensionality of the feature map, retaining the main features and reducing the amount of data, ultimately obtaining a preliminary feature vector containing key feature information. Finally, the preliminary feature vector is converted into quantum bit encoding form and input into the quantum annealing algorithm module; the quantum annealing algorithm uses quantum gate operations such as Hadamard gate and Pauli gate to rotate and entangle the quantum bits, remove redundant features, and optimize the combination of features to obtain a more compact and accurate data feature set, providing high-quality feature data for subsequent model construction.

[0034] In one embodiment, specifically, in step five, when constructing the signal characteristic model using quantum bits, a quantum gate circuit is used to construct the signal characteristic model, and the quantum gate circuit includes a single quantum bit gate and a multi-qubit gate; Quantum gate circuits are the basic operating modules of quantum computing, used to manipulate and evolve the state of quantum bits. Quantum gate circuits consist of a series of quantum gates, which are combined in a specific order and according to specific rules to process input quantum bits, thereby achieving specific computing tasks. When constructing signal feature models, quantum gate circuits can operate on encoded signal features (represented in the form of quantum bits), extracting and combining features to construct a model that can accurately describe the signal characteristics. Among them, a single-qubit gate is an operation that acts on a single qubit. It can change the state of a single qubit and realize operations such as rotation and flipping of the qubit state. Common single-qubit gates include Hadamard gates and Pauli gates. Multi-qubit gates are operations that act on multiple qubits. They can realize interaction and entanglement between qubits. Common multi-qubit gates include CNOT gates and Toffoli gates. When using quantum bits to construct a signal feature model, the extraction, conversion and combination of signal features can be achieved by rationally combining single-qubit gates and multi-qubit gates. For example, single-qubit gates are first used to perform preliminary processing on the features encoded by each quantum bit, such as creating a superposition state through a Hadamard gate to increase the range of feature search. Multi-qubit gates are then used to establish associations between different features, and the relationship between features is represented by an entangled state. Through a series of quantum gate operations, a model that can accurately describe the signal features can be gradually constructed, which can be used for subsequent tasks such as signal analysis and fault detection.

[0035] The method for constructing a signal feature model comprises the following steps: Step 501: Determine the number and initial state of quantum bits based on the dimension of the data feature set and the correlation between the features; Step 502: Using quantum gate circuits to operate on quantum bits, simulate the nonlinear relationship between signal data features, and construct a signal feature model; Step 503: Acquire known signal data samples and use the known signal data samples to train the signal feature model; the known signal data samples match the data feature set in terms of data type and feature dimension; Specifically, for example, in a metal card production and R&D laboratory, the data feature set contains 120 feature dimensions. The correlation between features is analyzed by calculating methods such as the Pearson correlation coefficient between the features. Based on the analysis results, it is determined that 60 quantum bits will be used to build the model. For feature groups with strong correlation, the initial state of the corresponding quantum bits is set to a mutually entangled state. For example, some quantum bits are initially in an entangled state of (|00>+|11>) / √2, and other quantum bits are set to the |0> or |1> state according to the feature conditions. Then, single-qubit gates (such as Pauli-X and Pauli-Y gates) are used to rotate a single qubit, changing its state and simulating changes in signal characteristics. Multi-qubit gates (such as CNOT gates) are used to entangle multiple qubits, simulating the complex nonlinear relationship between signal data characteristics and gradually building a signal characteristic model. Finally, 1,500 sets of known signal data samples were selected from past metal card production data. These samples cover signal data under normal production conditions and various common abnormal conditions, and match the current data feature set in terms of data type (current, voltage, magnetic field signals) and feature dimension; these samples are input into the constructed signal feature model for training. By continuously adjusting the parameters of the quantum gate circuit, such as the angle and time of gate operation, the model output is made close to the characteristics of the known samples, thereby improving the accuracy and generalization ability of the model.

[0036] In one embodiment, specifically, in step six, quantum key encryption uses the E91 quantum key distribution protocol to generate an encryption key, encrypts the data features and the standard features in the signal feature model, and calculates the cosine similarity between the encrypted feature vectors when performing pattern matching using the pattern matching algorithm of quantum key encryption. If the similarity is greater than a preset similarity threshold, the signal data is determined to be normal; if the similarity is less than the preset similarity threshold, the signal data is determined to be abnormal. At the same time, the system automatically triggers an early warning mechanism and records the abnormal signal data information to the blockchain distributed ledger. The E91 quantum key distribution protocol generates secure encryption keys based on the characteristics of quantum entanglement. The protocol mainly involves the following key steps: First, a sender (usually called Alice) and a receiver (usually called Bob) share a pair of entangled quantum particles (such as a pair of photons); entanglement means that the states of the two particles are correlated, no matter how far apart they are. Then, Alice and Bob independently and randomly select different measurement bases to measure the entangled particles they possess; the selection of the measurement basis is random and confidential; After the measurement is completed, Alice and Bob disclose their chosen measurement basis through a classical communication channel (such as the Internet), but do not disclose the measurement results. They will filter out the measurement results that use the same measurement basis, which constitute the original key. To ensure the security and accuracy of the key, they perform error correction on the original key to remove existing measurement errors, and then perform privacy amplification to further enhance the confidentiality of the key, ultimately obtaining a secure encryption key.

[0037] Cosine similarity is a method used to measure the similarity between two vectors. It expresses their similarity by calculating the cosine value of the angle between the two vectors. In step 6, the cosine similarity between the encrypted signal data feature vector and the standard feature vector is calculated. The specific calculation formula is:

[0038] in, and are the encrypted signal data eigenvector and the standard eigenvector, · represents the dot product of the vectors, and are the moduli of the two vectors respectively; the value range of cosine similarity is between -1 and 1. The closer the value is to 1, the more similar the two vectors are; the closer the value is to -1, the less similar the two vectors are. Specifically, for example, in the signal detection system of a large metal card manufacturer, a quantum key distribution device based on the E91 protocol was deployed; before the signal detection begins, the signal detection end and the signal feature model end generate a shared encryption key through the quantum channel; when the new signal data feature vector and the standard feature vector in the signal feature model are ready, they are encrypted using the generated encryption key; for example, each element in the feature vector is XORed with the corresponding element in the encryption key to obtain an encrypted feature vector; then the cosine similarity between the encrypted feature vectors is calculated, and the preset similarity threshold is 0.8; if the calculated similarity is 0.85, which is greater than the preset threshold, the system determines that the signal data is normal and the production process is proceeding normally; if the similarity is 0.78, which is less than the preset threshold, the system immediately triggers the sound and light warning mechanism, and at the same time records the acquisition time, equipment number, signal feature value, and abnormality type of the abnormal signal data to the blockchain distributed ledger for subsequent analysis and processing, so as to timely discover potential problems in the production process and ensure product quality.

[0039] In one embodiment, specifically, in step three, the low noise amplifier made of nanomaterials is a carbon nanotube field effect transistor amplifier; Among them, carbon nanotube field-effect transistors use carbon nanotubes as channel materials. When voltage is applied to the gate, the carrier concentration in the carbon nanotubes will change, thereby controlling the current flow between the source and drain, and realizing the signal amplification function; carbon nanotubes have excellent electrical properties, their internal electron mobility is high, and the noise introduced during the signal amplification process is small, which is especially important for processing weak signals, because low noise can ensure that the amplified signal is closer to the original signal, reducing interference and distortion; carbon nanotubes can respond to extremely weak signals and effectively amplify the signal intensity, thereby meeting the needs of subsequent signal processing; compared with traditional amplifiers, carbon nanotube field-effect transistor amplifiers consume less energy when working, which meets the requirements of low-power signal detection.

[0040] The smart contract compares the initial strength of the signal data with the preset strength threshold range. If the initial strength is lower than the first threshold, the gain is increased to the first gain level; if the initial strength is between the first and second thresholds, the gain is set to the second gain level; if the initial strength is higher than the second threshold, the gain is reduced to the third gain level. The smart contract dynamically adjusts the amplifier’s gain level by comparing the initial signal strength with a preset strength threshold. The specific rules are as follows: Initial strength is lower than the first threshold: When the initial strength of the signal data is lower than the first threshold, it indicates that the signal is very weak. In this case, the smart contract will increase the amplifier gain to the first gain level. A higher gain can enhance the signal amplitude, allowing the weak signal to be effectively identified and analyzed by subsequent processing modules. For example, in the metal card production process, if the initial strength of the detected current signal is too low to accurately determine the production status, increasing the gain can make the signal clearer. Initial strength is between the first and second thresholds: If the initial signal strength is between the first and second thresholds, indicating that the signal strength is within a moderate range, the smart contract will set the gain to the second gain level. This gain level ensures that the signal is properly amplified while avoiding signal distortion caused by over-amplification. Initial strength is higher than the second threshold: When the initial signal strength is higher than the second threshold, it means that the signal is already strong. To prevent signal distortion due to over-amplification, the smart contract will lower the gain to the third gain level, reducing the amplifier's amplification of the signal and ensuring that the signal is processed within a reasonable range. It should be noted that a smart contract is an automatically executed program that can make decisions quickly and accurately based on preset rules. In this signal detection system, the use of smart contracts to adjust the gain level is characterized by real-time and accuracy, and can promptly adapt to changes in signal strength, ensuring the stability and reliability of the entire signal detection process.

[0041] For example, in a small metal card production plant, the smart contract presets the following intensity threshold ranges: the first threshold is 0.5A, and the second threshold is 3A. When the initial intensity of the collected current signal is 0.3A, the smart contract determines that it is below the first threshold and automatically increases the gain of the carbon nanotube field-effect transistor amplifier to the first gain level, setting the gain to 12x. When the initial signal intensity is 2A, between the first and second thresholds, the smart contract sets the gain to the second gain level, such as 8x. When the initial signal intensity is 3.5A, above the second threshold, the smart contract lowers the gain to the third gain level, setting it to 4x. During the gain adjustment process, the smart contract monitors the amplifier's operating status in real time to ensure its stable operation and effectively amplify the filtered signal data to meet subsequent processing requirements.

[0042] By using carbon nanotube field-effect transistor amplifiers and smart contracts to dynamically adjust the gain level, the system can more effectively process signals of varying intensities, improve the accuracy and reliability of signal detection, and provide high-quality signal data for subsequent signal feature extraction and analysis.

[0043] In one embodiment, specifically, in step 1, signal data is acquired by collecting multi-dimensional signals from the metal card production equipment through a quantum sensor. The quantum sensor is a sensor based on a superconducting quantum interference device. The multi-dimensional signals from the metal card production equipment include current signals, voltage signals, and magnetic field signals. Among them, the superconducting quantum interference device (SQUID) is a highly sensitive magnetic measurement instrument based on the superconducting Josephson effect. In the superconducting state, electrons can flow without resistance. When a thin insulating layer (Josephson junction) exists between two superconductors, some special quantum phenomena occur. The SQUID is usually composed of a superconducting ring composed of one or more Josephson junctions. When an external magnetic field passes through this superconducting ring, it changes the magnetic flux within the ring. According to the principles of quantum mechanics, the change in magnetic flux causes the current in the superconducting ring to change. By detecting this change in current, the magnitude of the external magnetic field can be accurately measured. The multi-dimensional signal acquisition method is as follows: Current signal acquisition: In the circuits of metal card production equipment, changes in current generate certain magnetic fields. SQUID-based quantum sensors can indirectly measure current signals by detecting changes in these magnetic fields. For example, when metal card chip welding equipment is welding, instantaneous changes in current will generate corresponding magnetic field fluctuations around the equipment. SQUID can keenly capture these magnetic field changes and convert them into electrical signals, thereby obtaining relevant information about the current signal. Voltage signal acquisition: Although the SQUID is primarily used to measure magnetic fields, in some cases, voltage signals can be acquired indirectly. For example, in a circuit, changes in voltage cause changes in current, which in turn causes changes in the magnetic field. The SQUID detects changes in the magnetic field to reflect changes in voltage. Alternatively, by combining it with other circuit elements (such as resistors), the voltage signal can be converted into a current signal according to Ohm's law, which is then measured by the SQUID. Magnetic field signal acquisition: This is the main function of SQUID. Some components in metal card production equipment, such as motors and electromagnetic coils, will generate strong magnetic fields when working. SQUID can directly measure the strength, direction, distribution and other information of these magnetic fields. By analyzing the magnetic field signals, the operating status of the equipment can be understood, such as whether the motor is operating normally and whether the electromagnetic coil is working stably.

[0044] Quantum encryption technology uses the BB84 protocol in the quantum key distribution protocol. The two communicating parties generate a shared encryption key through the polarization state of a single photon and perform a one-time encryption operation on the signal data. The BB84 protocol is based on the fundamental principles of quantum mechanics, namely the non-cloning of quantum states and the fact that measurement perturbs quantum states. The polarization state of a single photon can be used to encode information. Common polarization states include horizontal (H), vertical (V), +45° (D), and -45° (A). The key generation process is as follows: Sender operation: The sender (assuming Alice) randomly selects the polarization state of a single photon to encode binary information, for example, horizontal polarization represents "0", vertical polarization represents "1", +45° polarization represents "0", and -45° polarization represents "1" (there are many encoding methods). Alice then sends these single photons with encoded information to the receiver (assuming Bob). Receiver operation: Bob randomly selects one of two measurement bases to measure the received single photon. The measurement basis can be the horizontal-vertical basis (for measuring horizontal and vertical polarization states) or the +45°-45° basis (for measuring +45° and -45° polarization states). Since Bob does not know the polarization state used by Alice when sending the photon, his measurement basis selection is random. Only when the measurement basis selected by Bob matches the polarization state used by Alice when sending the photon can he obtain a correct measurement result. Key screening: After the measurement is completed, Alice and Bob disclose the measurement basis information they used through a classic communication channel (such as ordinary network communication), but do not disclose the measurement results. They only retain those measurement results that have the same measurement basis, which constitute the shared original key. Error correction and privacy amplification: The original key contains some measurement errors, so error correction is required. Error correction algorithms are used to remove these errors. Privacy amplification is then performed to further enhance the confidentiality of the key, ultimately resulting in a secure shared encryption key. Once the shared encryption key is obtained, the communicating parties use it to perform a one-time, one-pad encryption operation on the signal data. Among them, one-time pad is a very secure encryption method, that is, each data block is encrypted using a different key. In this embodiment, the signal data collected from the metal card production equipment is XORed (or other encryption algorithms are used) with the corresponding key according to a fixed data block size to obtain the encrypted signal data. Since a different key is used for each encryption, even if an attacker intercepts part of the encrypted data and key, he cannot decrypt the other data blocks, thereby ensuring the security of the signal data during transmission and storage.

[0045] In summary, the embodiment of the present invention provides a low-power signal detection method in the metal card production process, which adopts a superconducting quantum interferometer sensor to collect multi-dimensional signals and quantum encrypt them, uses blockchain filtering and carbon nanotube amplifiers combined with smart contracts to adjust the gain, uses convolutional neural networks and quantum annealing algorithms to extract features, constructs and trains a quantum signal feature model, and uses quantum key encryption to detect signals based on the model. Abnormal information is recorded on the blockchain, achieving low-power and high-precision signal acquisition, effective interference removal, accurate feature extraction, precise detection of signal anomalies, ensuring data security, providing accurate data support for production monitoring and quality control, and improving the quality and stability of metal card production.

[0046] Figure 5 FIG. 1 is a functional module diagram of a low-power signal detection system in a metal card production process according to an embodiment of the present application. Figure 5 As shown, a low-power signal detection system for the metal card production process includes: a signal acquisition and encryption module, a blockchain filtering module, a low-noise amplification module, a feature extraction module, a model building and training module, and a signal detection module; a signal acquisition and encryption module configured to acquire signal data during the metal card production process and encrypt the signal data using quantum encryption technology; A blockchain filtering module is configured to filter the signal data using an adaptive filtering algorithm based on blockchain technology; The low-noise amplifier module is configured as a low-noise amplifier made of nanomaterials. It automatically adjusts the gain based on the initial strength of the signal data through smart contracts to amplify the filtered signal data. A feature extraction module is configured to extract features from the amplified signal data using a combination of an artificial intelligence algorithm and a quantum algorithm to obtain a data feature set; A model building and training module is configured to build a signal feature model using quantum bits based on the data feature set and train the signal feature model; The signal detection module is configured to perform signal data detection based on the established signal feature model and adopt a pattern matching algorithm of quantum key encryption to generate a detection result.

[0047] In one embodiment, the system further includes an energy management module, which is configured to use energy recovery technology to collect waste energy in the production environment and convert it into electrical energy storage, and combine it with dynamic power management technology to automatically reduce the operating frequency and voltage of the device to enter a low-power standby mode when there is no signal data processing; The application of energy recovery technology is as follows: There are many forms of waste energy in the metal card production environment; for example, the heat energy generated when the production equipment is in operation can be collected through a thermoelectric conversion device. This device uses the Seebeck effect to convert heat energy directly into electrical energy under the action of temperature difference; for example, the mechanical energy generated by the vibration of mechanical parts when the equipment is in operation can be converted into electrical energy with the help of piezoelectric materials; when the piezoelectric material is subjected to mechanical stress, an electric potential difference is generated at its two ends, thereby realizing energy collection; in addition, the electromagnetic radiation energy in the production environment can also be captured and converted through specific antennas and energy collection circuits; the collected electrical energy will be stored in rechargeable batteries or supercapacitors; rechargeable batteries have a high energy density and can store energy for a long time, which is suitable for scenarios with relatively stable energy demand; supercapacitors have the characteristics of fast charging and discharging, can provide a large amount of energy in a short time, and are very effective in responding to instantaneous high energy demand; by rationally configuring the combination of batteries and supercapacitors, it can be ensured that the stored electrical energy can stably and efficiently power the system.

[0048] The application of dynamic power management technology is as follows: When the system is idle and not processing any signal data, the energy management module automatically activates a dynamic power management mechanism. This mechanism reduces the device's operating frequency and voltage, putting it into a low-power standby mode. For example, the chip responsible for signal processing operates at a frequency of 1GHz and a voltage of 1.2V during normal operation. Once in low-power standby mode, the frequency drops to 100MHz and the voltage to 0.8V. This significantly reduces the device's power consumption, saving significant energy. The energy management module monitors the system's operating status in real time. Once new signal data needs to be processed, it can quickly switch the device from low-power standby mode back to normal operating mode. During the switching process, it gradually increases the device's operating frequency and voltage to ensure that the device can respond quickly and stably to signal processing needs, while avoiding damage caused by sudden voltage and frequency changes. Through the above functions of the energy management module, this system can not only effectively collect and utilize waste energy in the production environment, but also reduce power consumption when the equipment is idle, thereby significantly improving energy utilization efficiency and reducing energy waste, further reflecting the energy-saving advantages of the low-power signal detection method in the metal card production process.

[0049] In one embodiment, specifically, data interaction is performed between the signal acquisition and encryption module, the blockchain filtering module, the low-noise amplification module, the feature extraction module, the model construction and training module, and the signal detection module through an internal data interface; data interaction is performed through the internal data interface, so that the signal acquisition and encryption module, the blockchain filtering module, the low-noise amplification module, the feature extraction module, the model construction and training module, and the signal detection module can be organically combined to form a complete low-power signal detection system, which collaboratively completes the signal detection task in the metal card production process.

[0050] In summary, the embodiment of the present invention provides a low-power signal detection system for the metal card production process, which completes the detection task by collecting signals and encrypting, filtering, amplifying, extracting features, building a training model and detecting signals; in addition, the energy management module uses energy recovery and dynamic power management technology to reduce the idle power consumption of the equipment while collecting waste energy, thereby achieving low-power, high-precision signal detection and improving energy utilization.

[0051] For other details about the technical solutions for implementing each module in the low-power signal detection system in the metal card production process in the above embodiment, please refer to the description of the low-power signal detection method in the metal card production process in the above embodiment, which will not be repeated here.

[0052] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For system-related embodiments, since they are generally similar to method-related embodiments, their description is relatively simple. For relevant details, refer to the description of the method-related embodiments.

[0053] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0054] In the present disclosure, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "including," "comprising," "having," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0055] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0056] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0057] Various changes, substitutions, and modifications may be made to the technology described herein without departing from the teachings defined by the appended claims. Moreover, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of things, means, methods, and actions described above. Currently existing or later developed processes, machines, manufactures, compositions of things, means, methods, or actions that perform substantially the same function or achieve substantially the same results as the corresponding aspects described herein may be utilized. Accordingly, the appended claims include within their scope such processes, machines, manufactures, compositions of things, means, methods, or actions.

[0058] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0059] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A low-power signal detection method in the metal card production process, characterized in that: The following steps are involved: Obtain signal data during the metal card production process and encrypt the signal data using quantum encryption technology; Utilize the adaptive filtering algorithm based on blockchain technology to filter the signal data; A low-noise amplifier made of nanomaterials automatically adjusts the gain based on the initial strength of the signal data through smart contracts to amplify the filtered signal data; By combining artificial intelligence algorithms with quantum algorithms, feature extraction is performed on the amplified signal data to obtain a data feature set; Based on the data feature set, a signal feature model is constructed using quantum bits and then trained. Based on the established signal feature model, the pattern matching algorithm of quantum key encryption is used to detect signal data and generate detection results.

2. The low-power signal detection method in the metal card production process according to claim 1, characterized in that: The method for filtering signal data comprises the following steps: Import the received signal data into the blockchain-based filtering system, and record the initial information of the signal data to the blockchain distributed ledger; Analyze signal data using time domain analysis, frequency domain analysis, or time-frequency analysis to identify interference types and characteristics in the signal data; Adaptive filtering algorithms automatically adjust filter parameters based on the type and characteristics of interference present in the signal data; The signal data is filtered based on the filter with adjusted parameters to remove interference signals, and the filtering process and results are recorded on the blockchain.

3. The low-power signal detection method in the metal card production process according to claim 1, characterized in that: The artificial intelligence algorithm is a convolutional neural network, and the quantum algorithm is a quantum annealing algorithm; The method for obtaining the data feature set comprises the following steps: Convert the amplified signal data into a two-dimensional matrix form suitable for convolutional neural network input; Use the convolutional layer and pooling layer of the convolutional neural network to extract features from the signal data and obtain preliminary feature vectors; The preliminary feature vector is used as the input of the quantum annealing algorithm, which optimizes the combination of features through quantum bit encoding and quantum gate operations to obtain the data feature set.

4. The low-power signal detection method in the metal card production process according to claim 1, characterized in that: When constructing the signal characteristic model using quantum bits, a quantum gate circuit is used to construct the signal characteristic model, and the quantum gate circuit includes a single quantum bit gate and a multi-qubit gate; The method for constructing a signal feature model comprises the following steps: Determine the number and initial state of quantum bits based on the dimension of the data feature set and the correlation between the features; Use quantum gate circuits to operate quantum bits, simulate the nonlinear relationship between signal data characteristics, and build a signal feature model; Acquire known signal data samples and use the known signal data samples to train the signal feature model.

5. The low-power signal detection method in the metal card production process according to claim 1, characterized in that: The quantum key encryption uses the E91 quantum key distribution protocol to generate an encryption key, encrypts the data features and the standard features in the signal feature model, and calculates the cosine similarity between the encrypted feature vectors when performing pattern matching using the pattern matching algorithm of the quantum key encryption. If the similarity is greater than a preset similarity threshold, the signal data is determined to be normal; If the similarity is less than the preset similarity threshold, the signal data is judged to be abnormal. At the same time, the system automatically triggers the early warning mechanism and records the abnormal signal data information to the blockchain distributed ledger.

6. The low-power signal detection method in the metal card production process according to claim 1, characterized in that: The low-noise amplifier made of the nanomaterial is a carbon nanotube field-effect transistor amplifier; the smart contract compares the initial intensity of the signal data with a preset intensity threshold range. If the initial intensity is lower than the first threshold, the gain is increased to the first gain level; if the initial intensity is between the first threshold and the second threshold, the gain is set to the second gain level; if the initial intensity is higher than the second threshold, the gain is lowered to the third gain level.

7. The low-power signal detection method in the metal card production process according to claim 1, characterized in that: The signal data is acquired by collecting multi-dimensional signals of the metal card production equipment through a quantum sensor, wherein the quantum sensor is a sensor based on a superconducting quantum interference device, and the multi-dimensional signals of the metal card production equipment include current signals, voltage signals and magnetic field signals; The quantum encryption technology adopts the BB84 protocol in the quantum key distribution protocol. The communicating parties generate a shared encryption key through the polarization state of a single photon and perform a one-time encryption operation on the signal data.

8. A low-power signal detection system in a metal card production process, applied to a low-power signal detection method in a metal card production process according to any one of claims 1 to 7, characterized in that: The system includes: a signal acquisition and encryption module, a blockchain filtering module, a low-noise amplification module, a feature extraction module, a model building and training module, and a signal detection module; The signal acquisition and encryption module is configured to obtain signal data during the metal card production process and encrypt the signal data using quantum encryption technology; The blockchain filtering module is configured to filter the signal data using an adaptive filtering algorithm based on blockchain technology; The low-noise amplification module is configured as a low-noise amplifier made of nanomaterials, which automatically adjusts the gain through smart contracts according to the initial strength of the signal data to amplify the filtered signal data; The feature extraction module is configured to extract features from the amplified signal data using a combination of artificial intelligence algorithms and quantum algorithms to obtain a data feature set; The model building and training module is configured to build a signal feature model using quantum bits based on the data feature set and train the signal feature model; The signal detection module is configured to perform signal data detection based on the established signal feature model and adopt a pattern matching algorithm of quantum key encryption to generate a detection result.

9. The low-power signal detection system for metal card production according to claim 8, characterized in that: The system also includes an energy management module, which is configured to use energy recovery technology to collect waste energy in the production environment and convert it into electrical energy storage, and combine it with dynamic power management technology to automatically reduce the device's operating frequency and voltage to enter a low-power standby mode when there is no signal data processing.

10. The low-power signal detection system in the metal card production process according to claim 8, characterized in that: The signal acquisition and encryption module, blockchain filtering module, low-noise amplification module, feature extraction module, model construction and training module and signal detection module interact with each other through an internal data interface.

Images