Method, system and equipment for detecting elastic fabric

Abstract

The invention provides an elastic fabric detection method, system and equipment, which are applied to a detection system comprising an elastic fabric sensor network. The sensor is embedded into the elastic fabric; the detection method comprises the following steps: establishing a first node and a second node of the elastic fabric sensor network; the first node comprises the sensor; acquiring first data of the first node; performing encryption processing on the first data to obtain encrypted first data; performing ciphertext domain fusion processing on the encrypted first data by using the second node to obtain a feature matrix of the elastic fabric; the characteristic matrix represents an association relationship between grid coordinates of the elastic fabric and data of the sensor; encrypting the feature matrix and then sending the encrypted feature matrix to a terminal, so that the terminal decrypts the encrypted feature matrix and then generates a detection report of the elastic fabric; the detection report is used to decide the use of the elastic fabric.

Description

Technical Field

[0001] The present invention relates to the field of smart wearable and biosensor technology detection, and in particular to a detection method, system and equipment for elastic fabrics. Background Art

[0002] With the rapid development of smart wearable technology, accurate detection of temperature and pressure data related to textile touch has become a core requirement for functional clothing design, medical rehabilitation device development, and sports equipment optimization. However, existing technology systems suffer from the following bottlenecks: single data dimensions and inadequate tactile feature modeling. Existing textile touch detection technologies are mostly based on independent measurements of single physical quantities, lacking the ability to comprehensively analyze the spatiotemporal correlations of multimodal data such as temperature and pressure. This results in one-sided tactile feature extraction and an inability to accurately characterize dynamic comfort changes in textiles under complex scenarios. Dynamic adaptability is poor and real-time feedback is lacking. Traditional sensor networks use a fixed sampling frequency and static threshold judgment mechanism, making them difficult to adapt to the rapid, nonlinear changes in tactile parameters during human movement. Furthermore, the high latency of the data processing link prevents millisecond-level real-time warnings, severely limiting their application value in dynamic scenarios. The lack of synergy between hardware and algorithms is also a major challenge. Existing solutions focus on sensor hardware optimization but fail to achieve deep collaborative design of algorithms and hardware, leading to a significant conflict between massive sensor data and the limited computing power of edge devices. Privacy protection is lacking. Traditional solutions fail to encrypt sensitive information such as sensor data and system status. In multi-node collaboration or cloud-based interaction scenarios, there are risks of privacy leaks, such as data interception and sensor alliance collusion attacks. There is currently no effective solution to these issues. Summary of the Invention

[0003] The present invention provides a method, system and equipment for detecting elastic fabrics, which have the advantages of realizing spatiotemporal correlation analysis of multimodal data, improving dynamic adaptability and ensuring data privacy and security.

[0004] An embodiment of the present invention provides a method for detecting elastic fabric, which is applied to a detection system including an elastic fabric sensor network; the sensor is embedded in the elastic fabric; and the detection method includes: Establishing a first node and a second node of the elastic fabric sensor network; the first node includes the sensor; Acquire first data of the first node; encrypting the first data to obtain encrypted first data; Using the second node to perform ciphertext domain fusion processing on the encrypted first data to obtain a feature matrix of the elastic fabric; the feature matrix represents the correlation between the grid coordinates of the elastic fabric and the data of the sensor; The characteristic matrix is encrypted and sent to a terminal, so that the terminal decrypts the encrypted characteristic matrix and generates a test report of the elastic fabric; the test report is used to decide the use of the elastic fabric.

[0005] In some embodiments, the sensor includes a temperature sensor and / or a pressure sensor; and obtaining the first data of the first node includes: When the elastic fabric is subjected to temperature and / or pressure, temperature data from the temperature sensor and / or pressure data from the pressure sensor are acquired.

[0006] In some embodiments, the sensor further comprises a Bluetooth sensor; and the method further comprises: The unconfigured nodes in the elastic fabric sensor network are configured with the Bluetooth sensor.

[0007] In some implementations, encrypting the first data to obtain the encrypted first data includes: The first data is mapped and then encrypted using a preset homomorphic encryption technology to obtain the encrypted first data.

[0008] In some embodiments, performing ciphertext domain fusion processing on the encrypted first data using the second node to obtain a feature matrix of the elastic fabric includes: Using the second node to obtain the state matrix, observation matrix, control matrix, and gain matrix of the encrypted first data; Multimodal data fusion is performed on the state matrix, the observation matrix, the control matrix, and the gain matrix to obtain a feature matrix of the elastic fabric.

[0009] In some embodiments, the method further comprises: The dimension of the characteristic matrix is compressed to obtain a compressed characteristic matrix; the compressed characteristic matrix is encrypted and sent to the terminal.

[0010] In some embodiments, the method further comprises: Get the preset private key; Decrypting the encrypted characteristic matrix using the private key to obtain a decrypted characteristic matrix; A test report of the elastic fabric is generated based on the decrypted feature matrix.

[0011] In some embodiments, an RC filter network is connected in parallel to the output end of the sensor; and the method further comprises: When the elastic fabric is in an unloaded state, obtaining an output signal of the sensor; performing noise filtering on the output signal to obtain a digital signal corresponding to the output signal; Performing filtering on the digital signal to obtain a filtered digital signal; Noise compensation is performed on the filtered digital signal to obtain the first data.

[0012] An embodiment of the present invention further provides a detection system for elastic fabric, the detection system comprising elastic fabric, a temperature sensor and / or a pressure sensor, and a processing device; the temperature sensor and / or the pressure sensor are embedded in the elastic fabric; the temperature sensor and / or the pressure sensor form a sensor network; the temperature sensor is connected to a temperature sensor signal line; the pressure sensor is connected to a pressure sensor signal line; the processing device is connected to the temperature sensor signal line and the pressure sensor signal line, respectively; wherein, The temperature sensor signal line is used to obtain temperature data of the temperature sensor when the elastic fabric is subjected to temperature; The pressure sensor signal line is used to obtain pressure data of the pressure sensor when the elastic fabric is under pressure; The processing device is used to encrypt the temperature data and / or the pressure data to obtain encrypted first data; perform ciphertext domain fusion processing on the encrypted first data to obtain a feature matrix of the elastic fabric; the feature matrix represents the association between the grid coordinates of the elastic fabric and the data of the sensor; the feature matrix is encrypted and sent to the terminal, so that the terminal decrypts the encrypted feature matrix and generates a test report of the elastic fabric; the test report is used to decide the use of the elastic fabric.

[0013] An embodiment of the present invention further provides an elastic fabric detection device, which includes: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is used to execute the steps of the above-mentioned detection method when running the computer program.

[0014] An elastic fabric detection method provided in an embodiment of the present invention is applied to a detection system including elastic fabric; the sensor is embedded in the elastic fabric; the detection method comprises: establishing a first node and a second node of the elastic fabric sensor network; the first node includes the sensor; obtaining first data from the first node; encrypting the first data to obtain encrypted first data; performing ciphertext domain fusion processing on the encrypted first data using the second node to obtain a feature matrix of the elastic fabric; the feature matrix represents the association between the grid coordinates of the elastic fabric and the data from the sensor; encrypting the feature matrix and sending it to a terminal, so that the terminal decrypts the encrypted feature matrix and generates a detection report for the elastic fabric; the detection report is used to determine the use of the elastic fabric. The technical solution of the present application solves the problems of single data dimension and lack of privacy protection in traditional technologies by establishing sensor network nodes, encrypting multimodal data, and performing ciphertext domain fusion to generate a feature matrix. It has the advantages of realizing spatiotemporal correlation analysis of multimodal data, improving dynamic adaptability, and ensuring data privacy and security. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic flow chart of a method for detecting elastic fabric provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of a thin film temperature and pressure sensing network in an embodiment of the present application. In the figure, the pressure sensor signal line indicated by reference numeral 4 passes through the bottom of the elastic fabric base 6; Figure 3 A schematic diagram of a Bluetooth Mesh network constructed in an embodiment of the present application; Figure 4 Schematic diagram of an application scenario of the elastic fabric detection method in an embodiment of the present application; Figure 5 A schematic structural diagram of an elastic fabric detection system provided by an embodiment of the present invention; Figure 6 The figure is a schematic diagram of the hardware structure of the elastic fabric detection device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0017] The various specific technical features in the various embodiments described in the specific implementation methods can be combined in various ways without contradiction. For example, different implementation methods can be formed by combining different specific technical features. In order to avoid unnecessary repetition, the various possible combinations of the specific technical features in the present invention will not be described separately.

[0018] It should also be noted here that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions of the present invention are shown in the drawings, while other details that are not closely related to the present invention are omitted.

[0019] In addition, it should be noted that the terms "include", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the following description, the terms "first\second\..." involved are merely used to distinguish different objects and do not indicate that there is any similarity or connection between the objects. It should be understood that the directions described by the directional nouns such as "above", "below", "inside" and "outside" are all directions in normal use.

[0020] With the rapid development of smart wearable technology, accurate detection of temperature and pressure data related to textile touch has become a core requirement for functional clothing design, medical rehabilitation device development, and sports equipment optimization. However, the existing technology system has the following bottlenecks: 1. Single data dimension and insufficient tactile feature modeling: Existing textile tactile detection technologies are mostly based on the independent measurement of a single physical quantity. They lack the ability to comprehensively analyze the spatiotemporal correlation of multimodal data such as temperature and pressure. This leads to one-sided tactile feature extraction and the inability to accurately characterize the dynamic comfort changes of textiles in complex scenarios.

[0021] 2. Poor dynamic adaptability and lack of real-time feedback: Traditional sensor networks use a fixed sampling frequency and static threshold judgment mechanism, which makes it difficult to adapt to the rapid nonlinear changes in tactile parameters during human movement. In addition, the data processing link has a high latency and cannot achieve millisecond-level real-time warning, which seriously limits its application value in dynamic scenarios.

[0022] 3. Insufficient synergy between hardware and algorithms: Existing solutions focus on sensor hardware optimization but fail to achieve deep collaborative design of algorithms and hardware, resulting in a prominent contradiction between massive sensor data and the limited computing power of edge devices.

[0023] 4. Lack of privacy protection: Traditional solutions do not encrypt and protect sensitive information such as sensor data and system status. In multi-node collaboration or cloud interaction scenarios, there are risks of privacy leakage such as data interception and sensor alliance collusion attacks.

[0024] Based on this, the present invention provides a method for detecting elastic fabrics, such as Figure 1 As shown, Figure 1A flow chart of a method for detecting elastic fabric provided in an embodiment of the present invention is applied to a detection system including elastic fabric; the sensor is embedded in the elastic fabric; the detection method includes: Step S101: establishing a first node and a second node of the elastic fabric sensor network; the first node includes the sensor.

[0025] Step S102: Acquire first data of the first node.

[0026] Step S103: encrypt the first data to obtain encrypted first data.

[0027] Step S104: using the second node to perform ciphertext domain fusion processing on the encrypted first data to obtain a feature matrix of the elastic fabric; the feature matrix represents the association relationship between the grid coordinates of the elastic fabric and the data of the sensor.

[0028] Step S105: encrypt the characteristic matrix and send it to the terminal, so that the terminal decrypts the encrypted characteristic matrix and generates a test report of the elastic fabric; the test report is used to decide the use of the elastic fabric.

[0029] Among them, the elastic fabric sensor network refers to a distributed detection system composed of sensors embedded in the fabric, which can be specifically implemented by an array of temperature sensors and pressure sensors, and is used to synchronously collect multimodal tactile data. The first node refers to a data acquisition unit containing sensors, which can be specifically implemented by an embedded microcontroller, and is responsible for the acquisition and preliminary processing of raw data. Encryption processing refers to the mathematical transformation of raw data to prevent information leakage, which can be specifically implemented by a homomorphic encryption algorithm so that the data can still be calculated in an encrypted state. Ciphertext domain fusion processing refers to the execution of matrix operations in the encrypted data space, which can be specifically implemented by a Kalman filter algorithm, and features are extracted through iterative updates of the state matrix and the observation matrix. The feature matrix refers to a multidimensional data structure containing the association relationship between grid coordinates and sensor data, which can be specifically implemented by a sparse matrix encoding method, and is used to characterize the dynamic tactile distribution of elastic fabrics. Specifically, when an elastic fabric is subjected to external forces, the temperature or pressure sensor in the first node collects physical signals, which are converted into raw data through analog-to-digital conversion. This data is converted into ciphertext using a homomorphic encryption algorithm and transmitted to the second node, where matrix operations are performed without decryption, including state prediction, observation updates, and gain adjustment. The fused feature matrix is then used to generate a spatial distribution model using a grid coordinate mapping algorithm. This model is then re-encrypted and transmitted to the terminal device, which decrypts it using a private key to generate a test report containing the tactile intensity and distribution characteristics.

[0030] As an example, the sensor includes a temperature sensor and / or a pressure sensor; the first node can be called a child node; the second node can be called a master node; the master node is responsible for receiving and processing data from the temperature and pressure nodes, and the child node includes a temperature sensor and a pressure sensor, which is responsible for obtaining the value of each temperature and pressure sensor and uploading the data.

[0031] This invention achieves end-to-end data protection through a dual encryption mechanism. Existing technologies use a single sensor to independently process data, making it impossible to establish a spatial correlation model. This invention, however, uses a matrix fusion method to map discrete data into continuously distributed features. Existing systems rely on fixed thresholds to determine tactile states, while this invention utilizes a dynamic matrix update mechanism to adapt to nonlinear changes in elastic fabric deformation. Through the above-mentioned technical solution, this application achieves encrypted fusion processing of multimodal tactile data, solving the problems of single data dimension and insufficient privacy protection in traditional methods. Through matrix operations in the ciphertext domain, a spatial correlation model of tactile features is established while ensuring data security, improving the accuracy of detection results in dynamic scenarios. The terminal decryption and report generation mechanism ensures that end users can obtain complete tactile evaluation data, providing a reliable basis for the optimized design of medical rehabilitation assistive devices.

[0032] An embodiment of the present invention provides a method for detecting elastic fabrics. By establishing sensor network nodes, encrypting and processing multimodal data, and performing ciphertext domain fusion to generate a feature matrix, it solves the problems of single data dimension and lack of privacy protection in traditional technologies. It has the advantages of realizing spatiotemporal correlation analysis of multimodal data, improving dynamic adaptability, and ensuring data privacy and security.

[0033] In some embodiments, the sensor includes a temperature sensor and / or a pressure sensor; and obtaining the first data of the first node includes: When the elastic fabric is subjected to temperature and / or pressure, temperature data from the temperature sensor and / or pressure data from the pressure sensor are acquired.

[0034] A temperature sensor is a device capable of detecting surface temperature changes on an elastic fabric. Specifically, this can be implemented using a thermistor or thermocouple, and is used to monitor the fabric's temperature distribution in real time as it is heated. A pressure sensor is a device capable of sensing the intensity of pressure applied to the elastic fabric. Specifically, this can be implemented using a piezoelectric film or capacitive pressure sensor, and is used to capture the pressure distribution of the fabric as it is compressed. Temperature and pressure data are physical quantity signals collected by the temperature and pressure sensors, respectively. Specifically, an analog-to-digital conversion module can be used to convert analog signals into digital signals, which can be used to characterize the elastic fabric's response to various external influences.

[0035] Specifically, when the elastic fabric is subjected to external temperature or pressure, the temperature sensor and pressure sensor simultaneously start data acquisition. The temperature sensor senses changes in the fabric surface temperature through thermistors and generates temperature data; the pressure sensor detects the stress distribution in the compressed area of the fabric through the pressure-sensitive elements and generates pressure data. Both types of data are transmitted to the processing device via signal lines to form a multimodal data set. For example, in a medical rehabilitation scenario, when a patient wears elastic fabric for exercise, the temperature sensor can monitor local skin temperature changes, and the pressure sensor can simultaneously record the pressure distribution in the joint area. The data from both constitute the first data collected by the first node, providing multi-dimensional input for the subsequent feature matrix construction.

[0036] As an example, the temperature sensor utilizes a thin-film K-type thermocouple, which is adhesive and foldable, with a wide temperature measurement range (-20°C to 250°C) and an accuracy of up to 0.4°C, enabling accurate temperature measurement of textiles in various environments. The pressure sensor utilizes a flexible thin-film piezoresistor, which is foldable and has a wide pressure measurement range (20g to 20kg), sensitively detecting the deformation of textiles under varying pressures. By integrating the temperature and pressure sensors, a tactile feature matrix is constructed to enable spatiotemporal correlation analysis of multimodal data.

[0037] By integrating temperature and pressure sensors, this invention enables the simultaneous acquisition of multiple physical quantities, addressing the one-sided modeling of tactile characteristics caused by a single data dimension. Existing independent measurement methods struggle to capture the impact of temperature and pressure interactions on fabric performance. However, this invention, through multimodal data fusion, can more accurately characterize the dynamic response characteristics of fabrics under complex working conditions.

[0038] Through the above technical solution, this application achieves the simultaneous collection and joint analysis of temperature and pressure data, resolving the single-dimensional modeling issue of tactile characteristics in existing technologies. Through multimodal data fusion, it can more comprehensively reflect the dynamic response of elastic fabrics under complex external influences, providing multidimensional data support for subsequent feature matrix construction and improving the accuracy of test reports in determining fabric usage.

[0039] In some embodiments, the sensor further comprises a Bluetooth sensor; and the method further comprises: The unconfigured nodes in the elastic fabric sensor network are configured with the Bluetooth sensor.

[0040] A Bluetooth sensor is a sensor module that integrates the Bluetooth communication protocol. Specifically, it can be implemented using a low-power Bluetooth chip. It is used to establish a data transmission channel between devices within the wireless communication range. This module actively transmits device identification information via broadcast mode and supports two-way data encryption transmission protocols.

[0041] Unprovisioned nodes are isolated sensor units that have not yet been connected to the sensor network. Specifically, they may not have completed network address allocation or established communication links. These nodes appear during early deployment or when network topology changes occur, requiring dynamic discovery to identify and connect them. Specifically, during the deployment of a flexible fabric sensor network, Bluetooth sensors periodically transmit broadcast signals containing their network identifiers. When an unconnected node enters the signal's coverage area, its built-in Bluetooth module automatically detects the broadcast packet and triggers a pairing request. The pairing process utilizes a two-way authentication mechanism, such as a key exchange protocol based on elliptic curve cryptography. After identity verification, a dynamic network address is assigned. Once the network address is assigned, the node is incorporated into the sensor network topology and participates in subsequent data collection and transmission tasks.

[0042] As an example, the CH573 Bluetooth sensor is used to configure unconfigured nodes to achieve rapid formation and flexible configuration of the sensor network.

[0043] The present invention realizes wireless ad hoc networking through Bluetooth sensors, and nodes can independently complete network discovery and access without physical contact or preset gateway parameters, which significantly reduces deployment complexity. Through the above technical solution, this application realizes the dynamic expansion capability of the sensor network. Unconfigured nodes can independently complete identity authentication and network access, effectively solving the problem of incomplete network coverage caused by inefficient manual configuration in traditional solutions, while avoiding wiring interference caused by physical connections and improving the adaptability of sensor networks in elastic fabrics.

[0044] In some embodiments, encrypting the first data to obtain the encrypted first data includes: The first data is mapped and then encrypted using a preset homomorphic encryption technology to obtain the encrypted first data.

[0045] Homomorphic encryption technology refers to an encryption method that allows operations to be performed directly on encrypted data, and the decrypted result is consistent with the plaintext result. This can be achieved using an encryption algorithm based on ring learning errors. This technology allows the encrypted first data to be fused and processed even in the ciphertext state. Mapping processing refers to converting the original data into a mathematical structure suitable for homomorphic encryption operations. This can be achieved using vector encoding methods on polynomial rings. This step ensures that the sensor data is formatted and standardized before encryption.

[0046] Specifically, during the operation of the elastic fabric sensor network, the temperature or pressure data collected by the first node is first converted into a numerical vector of a preset dimension. This data is then converted into structured data using a polynomial ring mapping. This structured data is then input into the homomorphic encryption module, where it is encrypted using a preconfigured public key to generate an encrypted data packet containing a sequence of ciphertext coefficients. When the encrypted data packet is wirelessly transmitted to the second node, its ciphertext properties prevent the leakage of sensitive information during transmission. Upon receiving the encrypted data, the second node directly invokes the ciphertext operation protocol to complete the matrix fusion operation without decryption, keeping the data encrypted throughout the entire process.

[0047] As an example, using Pailliar partially homomorphic encryption technology, the child node encrypts the original data after mapping it to fixed-point numbers, and transmits it to the master node via Bluetooth Mesh. Specifically, the floating-point data collected by the sensor (such as temperature and pressure values) is encrypted through a fixed-point set. Q ( A , B ) are mapped to integers, Q ( A , B ) contains the interval (-2 A-B-1 , 2 A-B-1 -2 -B ) rational number, through the mapping function F ( A , B , b )=2 B b mod 2 A Convert to integer domain representation; where A and B can be understood as parameters in the fixed-point number mapping, used to convert floating-point data into integers; b It can be understood as an intermediate variable after the original floating-point data is mapped to a fixed-point number; F ( A , B , b ) can be understood as a fixed-point number mapping function. Using the encryption formula Enc ( d )= G d R N modN 2 Generate ciphertext, support ciphertext domain addition and scalar multiplication operations; among them, d It can be understood as raw data (such as temperature and pressure values); R It can be understood as a random number in the encryption process, satisfying , Representation model N The multiplication group of .

[0048] This invention uses homomorphic encryption technology to achieve full-process ciphertext processing, ensuring data privacy while maintaining data processing capabilities. Symmetric or asymmetric encryption methods used in existing technologies cannot support ciphertext domain operations and must rely on data fusion in a plaintext environment, which increases the risk of illegal data interception.

[0049] Through the above technical solution, this application realizes the encryption protection of sensor data throughout the entire process of collection, transmission, and processing, effectively preventing data leakage in multi-node collaborative scenarios. The encrypted data can be directly fused and calculated, avoiding the computing power loss caused by repeated encryption and decryption in traditional solutions, while ensuring the integrity of the feature matrix generation process.

[0050] In some embodiments, performing ciphertext domain fusion processing on the encrypted first data using the second node to obtain a feature matrix of the elastic fabric includes: Using the second node to obtain the state matrix, observation matrix, control matrix, and gain matrix of the encrypted first data; Multimodal data fusion is performed on the state matrix, the observation matrix, the control matrix, and the gain matrix to obtain a feature matrix of the elastic fabric.

[0051] In this embodiment, the state matrix refers to a data set containing the dynamic change characteristics of sensor data. Specifically, this can be achieved by dynamically modeling the encrypted data using a time series analysis model, and is used to characterize the real-time state evolution of the elastic fabric when it is subjected to external influences. The observation matrix refers to the set of actual sensor measurement data. Specifically, this can be achieved by decoupling the multi-source signal components in the encrypted data, and is used to reflect the measurement values of physical quantities at different spatial locations. The control matrix refers to a set of quantitative parameters that indicate the impact of external input variables on the system. Specifically, this can be achieved by dynamically calibrating the transmission parameters between nodes using an adaptive adjustment algorithm, and is used to balance network load and data processing accuracy. The gain matrix refers to a set of adjustment parameters for the weights of each modality during the data fusion process. Specifically, this can be achieved by dynamically weighting the encrypted data features using a pre-trained multi-objective optimization model, and is used to optimize the correlation between multi-source data. Multimodal data fusion refers to the joint calculation of heterogeneous data in an encrypted state. Specifically, this can be achieved using a matrix operation protocol based on homomorphic encryption, and can establish an association mapping between grid coordinates and sensor data while protecting data privacy. Specifically, during the ciphertext domain fusion process, the second node first parses the encrypted first data and separates the dynamic feature parameters in the state matrix and the spatial distribution parameters in the observation matrix through homomorphic operations. The control matrix dynamically adjusts the data transmission path according to the real-time network load, and the gain matrix iteratively optimizes the weights of temperature and pressure data. In the multimodal data fusion stage, the four matrices are jointly operated in an encrypted state. For example, matrix multiplication is used to achieve spatiotemporal feature coupling, and matrix addition is used to complete the superposition of multi-source data. The final generated feature matrix stores the comprehensive tactile parameters of each grid point of the elastic fabric under different working conditions in an encrypted form. As an example, after receiving encrypted data, the edge node uses the state update formula: Enc ( Z k+1 )=( S - T × C )× Enc ( Z k )⊕ U × Enc ( U k ⊕ V × Enc ( Y k );in, Z k 、 Z k+1 It can be understood as a state variable, used for status updates in ciphertext processing; S It can be understood as a state matrix, a parameter in ciphertext processing; T It can be understood as the observation matrix, the parameter in ciphertext processing; U It can be understood as a control matrix, a parameter in ciphertext processing; V It can be understood as a gain matrix, a parameter in ciphertext processing; U k 、Y k It can be understood as an input variable used for ciphertext processing calculations; it completes multimodal data fusion and avoids plaintext exposure.

[0052] The present invention establishes nonlinear associations between data in the ciphertext domain by constructing four types of functional matrices, which not only solves the problem of missing spatiotemporal correlation of multimodal data, but also avoids the risk of privacy leakage during data processing. Through the above technical solution, this application can realize dynamic correlation analysis of temperature and pressure data in an encrypted environment, improve the integrity of the tactile feature modeling of elastic fabrics, and at the same time ensure data transmission security through ciphertext domain matrix operations, solving the dual problems of the traditional solution's single data dimension and lack of privacy protection.

[0053] In some embodiments, the method further comprises: The dimension of the characteristic matrix is compressed to obtain a compressed characteristic matrix; the compressed characteristic matrix is encrypted and sent to the terminal.

[0054] Compressing the dimensions of a feature matrix refers to reducing the number of matrix dimensions through a dimensionality reduction algorithm. This can be achieved using principal component analysis or linear discriminant analysis. Orthogonal transformations are used to project high-dimensional data into a low-dimensional space, removing redundant information and retaining key feature dimensions. The compressed feature matrix is the low-dimensional data set formed after dimensionality reduction. This can be achieved using matrix decomposition or feature selection methods. By reducing the data dimension, the amount of transmitted data is reduced while maintaining the integrity of feature relationships.

[0055] Specifically, after generating a feature matrix representing the relationship between the elastic fabric mesh coordinates and sensor data, the matrix is compressed using a preset dimensionality reduction algorithm. For example, principal component analysis is used to extract the principal component with the largest variance in the matrix, mapping the original high-dimensional matrix to a low-dimensional space to eliminate the linear correlation between temperature and pressure data. During the compression process, the eigenvalues and eigenvectors of the covariance matrix are calculated, and the principal components with contribution rates exceeding a set threshold are selected to construct a low-dimensional feature matrix. The resulting compressed matrix retains the spatiotemporal correlation of the fabric's tactile characteristics while significantly reducing the data size, facilitating subsequent encrypted transmission.

[0056] As an example, using the reduced-order operator Red ( Q ) compresses the ciphertext dimension and uses a conservative strategy to ensure that the reduced-order region contains the original state estimation range. The formula is: Enc ( )= Red ( Q )× Enc ( Z k+1 );in, Q It can be understood as the parameter of the reduction operator, which is usually related to the accuracy of the ciphertext data and the dimension of the state space. The specific value needs to be set according to the actual needs of the sensor network; Red(Q) It can be understood as a reduction operator for ciphertext processing. Its main function is to compress the dimension of ciphertext data, reduce computational complexity, and ensure the accuracy of state estimation. Enc(Z k+1 ) It can be understood as the original ciphertext state variable; Enc ( ) can be understood as the reduced-order ciphertext; it reduces the computational complexity while ensuring the estimation accuracy.

[0057] The present invention introduces dimensionality compression processing to actively reduce the dimension of the feature matrix before data encryption, which not only reduces the amount of ciphertext data to improve transmission efficiency, but also avoids the waste of storage resources due to data redundancy, while ensuring the integrity of feature information by retaining the principal components.

[0058] Through the above technical solution, this application effectively solves the problem of low transmission efficiency of high-dimensional feature matrices, actively reduces the data dimension before the encryption link, reduces the communication resource consumption required for ciphertext transmission, and maintains detection accuracy by retaining the main component features, thereby realizing efficient operation of the detection system under limited bandwidth conditions.

[0059] In some embodiments, the method further comprises: Get the preset private key; Decrypting the encrypted characteristic matrix using the private key to obtain a decrypted characteristic matrix; A test report of the elastic fabric is generated based on the decrypted feature matrix.

[0060] The private key refers to the decryption key paired with the public key encryption algorithm. Specifically, this can be achieved using an RSA private key or an elliptic curve encryption private key in an asymmetric encryption algorithm, and is used to uniquely authorize the decryption of encrypted data. The decrypted feature matrix refers to the original data matrix restored through private key operations. Specifically, this can be achieved using a homomorphic decryption algorithm or a layered decryption protocol, ensuring that ciphertext data is restored to parsable plaintext data on the terminal side. The test report is a structured document containing the results of the fabric condition assessment. Specifically, a machine learning model can be used to perform pattern recognition on the feature matrix and generate a visual chart to guide decisions about fabric usage.

[0061] Specifically, a private key paired with the encryption public key is pre-stored on the terminal device. Upon receiving the encrypted feature matrix, the private key is used to perform a decryption operation to restore the original data format. The decrypted feature matrix uses a coordinate mapping algorithm to analyze the correspondence between sensor data and the fabric mesh. Based on a pre-set fabric performance evaluation model, a test report is automatically generated, including temperature distribution maps, pressure thermodynamic maps, and comprehensive scoring indicators. The entire decryption process is completed in a secure execution environment, ensuring that sensitive data is only readable by authorized terminals.

[0062] As an example, a user performs a decryption operation using a private key: Dec ( Enc ( d )= L [( Enc ( d ) λ mod N 2 )]× MmodN; Wherein, L(x) is an auxiliary function, for example, L(x)=(x-1) / N; restore the plaintext result and complete the data closed-loop processing.

[0063] The present invention builds an end-to-end data security link by binding private keys to authorized terminals, ensuring multi-node collaborative computing while achieving controlled access to terminal data.

[0064] Through the above technical solution, this application effectively prevents the feature matrix from being parsed by unauthorized devices on the terminal side, avoiding the risk of sensor network data leakage in the final application. Combining decryption operations with an automated report generation process improves the efficiency and accuracy of test results while ensuring data privacy, providing a reliable basis for decision-making on fabric usage.

[0065] In some embodiments, an RC filter network is connected in parallel to the output end of the sensor; and the method further comprises: When the elastic fabric is in an unloaded state, obtaining an output signal of the sensor; performing noise filtering on the output signal to obtain a digital signal corresponding to the output signal; Performing filtering on the digital signal to obtain a filtered digital signal; Noise compensation is performed on the filtered digital signal to obtain the first data.

[0066] The RC filter network refers to a filter circuit composed of resistors and capacitors. Specifically, it can be implemented using a low-pass filter with a cutoff frequency of 10Hz-1kHz to filter out high-frequency interference signals from the sensor output signal. Noise filtering refers to the initial noise reduction processing of the sensor's raw signal. Specifically, it can be implemented using a sliding window averaging algorithm or a wavelet threshold denoising algorithm to eliminate baseline drift caused by environmental electromagnetic interference. Filtering refers to secondary noise reduction of the digital signal. Specifically, it can be implemented using a Butterworth low-pass filter or a Kalman filter to suppress random noise during signal transmission. Noise compensation refers to the dynamic compensation of residual noise. Specifically, it can be implemented using an adaptive compensation algorithm based on a historical noise database to eliminate signal distortion caused by temperature drift or circuit noise.

[0067] Specifically, when the elastic fabric is unloaded and unaffected by external forces, the sensor output signal contains only ambient noise and circuit background noise. At this point, the sensor analog signal undergoes primary filtering through a parallel RC filter network, attenuating high-frequency interference signals to below a preset threshold. The digital signal, after analog-to-digital conversion, is input into a noise filtering module, where a sliding window averaging algorithm performs weighted averaging on consecutive sampling points to eliminate sudden pulse interference. The signal is then processed in the frequency domain using a Butterworth low-pass filter to suppress out-of-band noise components. Finally, an adaptive compensation algorithm is employed to dynamically compensate for residual noise based on a preset no-load reference value, ensuring that the sensor output in the no-load state remains stable within the allowable error range.

[0068] As an example, a two-stage noise suppression strategy: a. Hardware-level noise filtering algorithm: An RC filter network is connected in parallel to the output of the pressure sensor with the following parameters: resistor R = 1kΩ, capacitor C = 10μF. Cutoff frequency calculation: , effectively attenuating high-frequency noise above 20Hz (such as high-frequency interference caused by motion friction); among them, f c It can be understood as the cutoff frequency, which is used to calculate the noise attenuation range of hardware filtering. Collect the sensor output signal in the no-load state and calculate the noise mean. μ n and standard deviation σ n , used for noise compensation on the algorithm side. b. Dynamic filtering algorithm at the algorithm layer: Adaptive window initialization: Integrate a three-axis accelerometer to monitor the human body's motion state in real time. In static state: acceleration amplitude |a| < 0.2g, set the filter window N = 50 (corresponding to 100ms). In motion state: |a| ≥ 0.2g, the window is dynamically reduced to N = 10 (corresponding to 20ms) to improve real-time performance. Dynamic moving average filtering: for temperature / pressure digital signals x k Perform a sliding window average: When the window slides, remove more than μ n ±3 σ n The abnormal value (based on the statistical characteristics of hardware noise) is calculated and the mean is calculated. Noise compensation correction: the signal after filtering is y k Perform trend elimination and remove low-frequency drift noise through median filtering: (2) Energy consumption optimization design: Set energy-saving mode and automatically switch to microampere sleep mode when in standby state; use data compression transmission technology to compress 12-bit original data to 8-bit, reducing energy consumption while ensuring data quality.

[0069] Traditional solutions lack a no-load calibration step, allowing the sensor's background noise and environmental interference to be directly superimposed on the effective signal, reducing data acquisition accuracy. Existing single-order filter designs cannot address broadband noise suppression requirements and lack dynamic compensation mechanisms, making them prone to signal distortion in complex electromagnetic environments.

[0070] Through the above technical solution, the present application effectively reduces the impact of sensor background noise and environmental interference on data acquisition, improving the signal-to-noise ratio and accuracy of the first data. The multi-stage signal processing process in the no-load state establishes the sensor's baseline operating state, providing a reliable reference for subsequent data acquisition in the loaded state and avoiding system misjudgments caused by noise accumulation.

[0071] In practical applications, the elastic fabric detection method may be a detection method for a distributed elastic fabric temperature and pressure detection sensor network for textile tactile testing, comprising: 1. Multimodal detection: Integrate temperature and pressure sensors to build a tactile feature matrix to realize spatiotemporal correlation analysis of multimodal data.

[0072] 2. Dynamic adaptation: Dynamically optimize the sampling frequency based on the human body's motion state to adapt to rapid changes in tactile parameters.

[0073] 3. Collaborative optimization: RC filtering on the hardware side and dynamic filtering on the algorithm side jointly reduce noise and improve signal quality.

[0074] 4. Encrypted transmission: Pailliar homomorphic encryption is used to encrypt sensor data end-to-end to protect privacy.

[0075] 5. Anti-collusion attacks: The fully symmetric polytope encryption structure combined with reduced-order operators defends against collusion attacks and data inference.

[0076] The present invention mainly embeds a temperature and pressure sensor array into elastic fabrics and builds a sensor network through Bluetooth Mesh networking technology to achieve distributed real-time monitoring of the touch of textiles. The details are as follows: 1. Smart fabric sensor network architecture.

[0077] (1) Sensor layer: Temperature sensor: It uses a thin film K-type thermocouple, which has the characteristics of being sticky and foldable, with a wide temperature measurement range (-20~250℃) and an accuracy of up to 0.4℃. It can accurately measure the temperature of textiles in different environments.

[0078] Pressure sensor: It uses a flexible thin film piezoresistor, which is foldable and has a wide pressure measurement range (20g~20kg). It can sensitively sense the deformation of textiles under different pressures.

[0079] Sensor network design: By optimizing sensor layout and wiring, the number of wiring can be reduced while obtaining all measurement data, thus improving the reliability and stability of the sensor network. Figure 2 To understand, Figure 2 Schematic diagram of the thin film temperature and pressure sensing network in the embodiment of the present application. Figure 2 In the figure, 1 may be a thin film pressure sensor; 2 may be a thin film temperature sensor; 3 may be a sensor network; 4 may be a pressure sensor signal line; 5 may be a temperature sensor signal line; and 6 may be an elastic fabric base.

[0080] (2) Communication layer.

[0081] Bluetooth Mesh network construction: It includes a master node and sub-nodes. The master node is responsible for receiving and processing data from the temperature and pressure nodes. The sub-node contains a temperature sensor and a pressure sensor, and is responsible for obtaining the value of each temperature and pressure sensor and uploading the data.

[0082] Data transmission optimization: Use CH573 Bluetooth sensors to configure unconfigured nodes, enabling rapid formation and flexible configuration of sensor networks.

[0083] Encrypted transmission: Using Pailliar partially homomorphic encryption technology, the child node performs fixed-point mapping on the original data and encrypts it before transmitting it to the master node via Bluetooth Mesh.

[0084] This content can be combined Figure 3 To understand, Figure 3 This is a schematic diagram of the Bluetooth Mesh network construction in the embodiment of this application.

[0085] 2. Data encryption and processing (1) Key generation: Generate two large prime number pairs P and Q , calculate the modulus N = PQ and auxiliary parameters λ = lcm ( P -1, Q -1), construct the public key pk = ( N , G )( G = N +1) with private key sk =( λ , M )( M is the modular inverse element), used for subsequent encryption and decryption operations; P and Q It can be understood as two large prime numbers used to generate the key P andQ It can be understood as two large prime numbers used when generating keys; N It can be understood as a modulus, P and Q Calculated; λ Can be understood as auxiliary parameters, λ =lcm( P -1, Q -1), where lcm represents the least common multiple; G It can be understood as a component of the public key. G = N + 1; pk It can be understood as a public key. pk = ( N , G ); sk It can be understood as a private key. sk = ( λ , M ),in M is a modular inverse element, satisfying M = ( λ mod N) -1 .

[0086] (2) Data encryption: The floating point data collected by the sensor (such as temperature and pressure values) is collected through fixed point numbers Q ( A , B ) are mapped to integers, Q ( A , B ) contains the interval (-2 A-B-1 , 2 A-B-1 -2 -B ) rational number, through the mapping function F ( A , B , b )=2 B b mod 2 A Convert to integer domain representation; where A and B can be understood as parameters in the fixed-point number mapping, used to convert floating-point data into integers; b It can be understood as an intermediate variable after the original floating-point data is mapped to a fixed-point number; F ( A , B , b ) can be understood as a fixed-point number mapping function.

[0087] Using encryption formula Enc ( d )= G d RN modN 2 ( R is a random number, ) generates ciphertext, supporting ciphertext domain addition and scalar multiplication operations; among them, d It can be understood as raw data (such as temperature and pressure values); R It can be understood as a random number in the encryption process, satisfying , Representation model N The multiplication group of .

[0088] (3) Ciphertext processing: After the edge node receives the encrypted data, it updates the state through the formula: Enc ( Z k+1 )=( S - T × C )× Enc ( Z k )⊕ U × Enc ( U k ⊕ V × Enc ( Y k ); in, Z k 、 Z k+1 It can be understood as a state variable, used for status updates in ciphertext processing; S It can be understood as a state matrix, a parameter in ciphertext processing; T It can be understood as the observation matrix, the parameter in ciphertext processing; U It can be understood as a control matrix, a parameter in ciphertext processing; V It can be understood as a gain matrix, a parameter in ciphertext processing; U k 、Y k It can be understood as an input variable and is used for ciphertext processing calculations.

[0089] Complete multimodal data fusion to avoid plaintext exposure. S is the state matrix, T is the observation matrix, U is the control matrix, V is the gain matrix.

[0090] (4) Reduced-order optimization: Using reduced-order operators Red (Q ) compresses the ciphertext dimension and uses a conservative strategy to ensure that the reduced-order region contains the original state estimation range. The formula is: Enc ( )= Red ( Q )× Enc ( Z k+1 ); in, Q It can be understood as the parameter of the reduction operator, which is usually related to the accuracy of the ciphertext data and the dimension of the state space. The specific value needs to be set according to the actual needs of the sensor network; Red(Q) It can be understood as a reduction operator for ciphertext processing. Its main function is to compress the dimension of ciphertext data, reduce computational complexity, and ensure the accuracy of state estimation. Enc (Z k+1 ) It can be understood as the original ciphertext state variable; Enc ( ) can be understood as the reduced-order ciphertext.

[0091] Reduce computational complexity while ensuring estimation accuracy.

[0092] (5) Decryption verification: The user performs decryption operation using the private key: Dec ( Enc ( d )= L [( Enc ( d ) λ mod N 2 )]× MmodN ; Wherein, L(x) is an auxiliary function, for example, L(x)=(x-1) / N.

[0093] Restore the plaintext results and complete the data closed-loop processing.

[0094] 3. Hardware-algorithm collaborative optimization (1) Two-stage noise suppression strategy: a. Hardware noise filtering algorithm: An RC filter network is connected in parallel to the output of the pressure sensor, with the following parameters: resistor R = 1kΩ, capacitor C = 10μF.

[0095] Cutoff frequency calculation: , effectively attenuating high-frequency noise above 20Hz (such as high-frequency interference caused by motion friction); among them, fc It can be understood as the cutoff frequency, which is used to calculate the noise attenuation range of hardware filtering.

[0096] Collect the sensor output signal in the no-load state and calculate the noise mean μ n and standard deviation σ n , used for algorithm-side noise compensation.

[0097] b. Dynamic filtering algorithm at the algorithm layer.

[0098] Adaptive Window Initialization: An integrated three-axis accelerometer monitors human motion in real time. In static state, when acceleration amplitude |a| is less than 0.2g, the filter window N is set to 50 (corresponding to 100ms). In motion, when |a| is greater than or equal to 0.2g, the window is dynamically reduced to N = 10 (corresponding to 20ms), improving real-time performance.

[0099] Dynamic moving average filtering: for temperature / pressure digital signals x k Perform a sliding window average: When the window slides, remove more than μ n ±3 σ n The outliers are detected (based on the statistical characteristics of hardware noise) and then the mean is calculated.

[0100] Noise compensation correction: for the filtered signal y k Perform trend elimination and remove low-frequency drift noise through median filtering: .

[0101] (2) Energy consumption optimization design: Set the energy-saving mode and automatically switch to the microampere sleep mode when in a static state; use data compression transmission technology to compress 12-bit original data to 8 bits, reducing energy consumption while ensuring data quality.

[0102] The schematic diagram of the application scenario of the detection method of elastic fabric of the present invention is as follows Figure 4 As shown, Figure 4 This is a schematic diagram of an application scenario of the elastic fabric detection method in the embodiment of this application. Its working method is as follows: 1. Initialization and networking: When the system starts, the master node configures the network for the unconfigured nodes through the CH573 Bluetooth sensor to build a complete Bluetooth Mesh network. The master node distributes the public key to all child nodes. pk , private key sk Securely stored by the user terminal.

[0103] 2. Encrypted data collection and transmission: When the textile is subjected to pressure / temperature stimulation, the child node collects data and performs fixed-point number mapping and Pailliar encryption, and transmits it to the master node in real time via Bluetooth Mesh.

[0104] 3. Data processing and analysis: The master node uses the Pailliar encryption algorithm to perform ciphertext fusion analysis on the encrypted temperature and pressure data transmitted by the sensor layer. Specifically, the tactile feature matrix is constructed through the following steps: (1) Ciphertext state update: Based on the sensor's historical encrypted data, real-time encrypted measurement values, and control parameters (such as sampling frequency and threshold settings), the state estimation set is updated through homomorphic operations. Combined with the state matrix, observation matrix, and gain matrix, the spatiotemporal correlation calculation of multimodal data is completed without decryption.

[0105] (2) Feature extraction and quantification: Extract key feature parameters such as temperature distribution uniformity and pressure change gradient from the updated encrypted data, and construct a two-dimensional tactile feature matrix, where the rows and columns are the grid coordinates of the fabric surface and the elements are the temperature-pressure correlation eigenvalues.

[0106] 4. Result Output and Feedback: The master node transmits the encrypted analysis results to the cloud or host computer. Users decrypt the encrypted results using their private key, ultimately obtaining a visual plaintext report for decision-making in textile R&D, production, or quality testing.

[0107] 5. Maintenance and Expansion: The sensor network is easy to expand and maintain. Adding or removing sensor nodes is simple via the Bluetooth Mesh network's configuration capabilities. Furthermore, the system supports remote monitoring and maintenance, allowing users to monitor the sensor network's operating status and make necessary adjustments.

[0108] The embodiment of the present invention further provides a detection system 500 for elastic fabrics, such as Figure 5 As shown, Figure 5 This is a schematic structural diagram of an elastic fabric detection system provided by an embodiment of the present invention. The structure and function of the detection system are exemplarily described below in conjunction with various embodiments.

[0109] The detection system 500 includes an elastic fabric 501, a temperature sensor 502 and / or a pressure sensor 503, and a processing device 504; the temperature sensor 502 and / or the pressure sensor 503 are embedded in the elastic fabric 501; the temperature sensor 502 and / or the pressure sensor 503 form a sensor network; the temperature sensor 502 is connected to a temperature sensor signal line; the pressure sensor 503 is connected to a pressure sensor signal line; the processing device 504 is connected to the temperature sensor signal line and the pressure sensor signal line respectively; wherein, The temperature sensor signal line is used to obtain temperature data of the temperature sensor 502 when the elastic fabric is subjected to temperature; The pressure sensor signal line is used to obtain pressure data from the pressure sensor 503 when the elastic fabric is under pressure; The processing device 504 is used to encrypt the temperature data and / or the pressure data to obtain encrypted first data; perform ciphertext domain fusion processing on the encrypted first data to obtain a feature matrix of the elastic fabric; the feature matrix represents the association between the grid coordinates of the elastic fabric and the data of the sensor; encrypt the feature matrix and send it to the terminal, so that the terminal decrypts the encrypted feature matrix and generates a test report of the elastic fabric; the test report is used to decide the use of the elastic fabric.

[0110] Elastic fabric refers to a stretchable textile material, specifically a blend of polyurethane and cotton fibers. Its grid coordinates are located by nodes formed by interweaving warp and weft yarns. The temperature sensor signal line refers to the conductive circuit connecting the temperature sensor to the processing device, specifically a silver-plated fiber braided wire. It is used to maintain signal transmission stability when the fabric is deformed by heat. Ciphertext domain fusion processing refers to performing data fusion operations in an encrypted state. This can be achieved by using a homomorphic encryption algorithm combined with the Kalman filter equation. This allows for multimodal data association analysis while protecting data privacy.

[0111] Specifically, when the elastic fabric is subjected to external temperature or pressure, the temperature and pressure sensors embedded in the fabric transmit the collected physical quantity data to a processing device via dedicated signal lines. The processing device first homomorphically encrypts the raw data, allowing subsequent calculations to be performed in an encrypted state. The encrypted temperature and pressure data are then input into a fusion algorithm module, which constructs a state matrix and an observation matrix to perform multi-dimensional data correlation, ultimately generating a feature matrix reflecting the distribution of sensor data at each grid point in the fabric. This matrix is then encrypted again and transmitted to a terminal device, where an authorized user decrypts it using a private key to generate a test report containing the fabric's performance parameters.

[0112] In some specific embodiments, temperature sensor signal lines can be embedded in the warp yarns of the fabric, while pressure sensor signal lines can be embedded in the weft yarns. This interweaving of the warp and weft yarns forms a signal transmission network. The processing device can be integrated into a flexible printed circuit board at the edge of the fabric, using a low-power Bluetooth module to establish a communication connection with the terminal. The characteristic matrix can be encrypted using a layered encryption mechanism based on elliptic curve cryptography, ensuring end-to-end protection during data transmission.

[0113] Compared to existing technologies, traditional detection systems rely on a single sensor type operating independently, making it impossible to simultaneously acquire fabric performance data under the coupled effects of temperature and pressure. This invention achieves parallel acquisition of multiple physical quantities by constructing dual signal transmission channels. Combined with a ciphertext domain fusion algorithm, this approach effectively addresses the issue of single data dimension. While existing sensor networks often use plaintext transmission, this invention implements encryption protection throughout the entire data acquisition, processing, and transmission process, significantly improving system security.

[0114] Through the above technical solution, this application achieves the simultaneous encrypted collection and fusion analysis of temperature and pressure data, addressing the technical shortcomings of traditional detection systems, such as the single data dimension and weak privacy protection. The ability to analyze the spatiotemporal correlation of multimodal data enables more comprehensive evaluation of fabric performance, and the encrypted transmission mechanism effectively prevents the theft of sensitive data during transmission, providing reliable protection for the secure application of smart textiles.

[0115] The temperature sensor signal line refers to the signal transmission channel connecting the temperature sensor and the processing device. It can be implemented using flexible conductive materials or metal wires and is used to transmit temperature data when the elastic fabric is subjected to temperature. The pressure sensor signal line refers to the signal transmission channel connecting the pressure sensor and the processing device. It can be implemented using pressure-sensitive conductive fabric or a strain gauge structure and is used to transmit pressure data when the elastic fabric is subjected to pressure. The processing device refers to a computing module with data encryption and fusion capabilities. It can be implemented using an embedded processor combined with a homomorphic encryption algorithm and is used to encrypt multimodal sensor data and perform ciphertext domain fusion operations.

[0116] Specifically, the temperature sensor signal lines and the pressure sensor signal lines respectively capture the physical changes in the elastic fabric under the influence of temperature or pressure, and transmit the raw data via these lines to a processing device. The processing device homomorphically encrypts the received temperature and pressure data, allowing fusion operations to be performed even in an encrypted state. The encrypted data undergoes multimodal fusion using a Kalman filter algorithm, generating a feature matrix that reflects the correlation between the sensor data at each grid point of the elastic fabric. This feature matrix is then encrypted again and transmitted to the terminal device, which decrypts it using a private key to generate a test report containing the fabric's performance parameters, providing data support for subsequent use decisions.

[0117] The present invention realizes separate collection of physical quantities and avoids signal crosstalk by independently setting up temperature and pressure sensor signal lines; the processing device directly performs data fusion in the ciphertext domain, which not only ensures data security but also reduces the decryption calculation amount and improves the real-time performance of the system.

[0118] Through the above technical solution, this application solves the problems of poor spatiotemporal correlation and lack of privacy protection in multimodal data. Through signal line isolation and ciphertext domain fusion technology, it realizes the precise synchronous collection and secure transmission of temperature and pressure data, while reducing data processing delay, providing a reliable data basis for fabric performance evaluation in dynamic scenarios.

[0119] Figure 6 This is a hardware structure diagram of an elastic fabric detection device according to an embodiment of the present invention. The elastic fabric detection device 600 includes: at least one processor 601, a memory 602, and optionally, the elastic fabric detection device 600 may further include at least one communication interface 603. The various components in the elastic fabric detection device 600 are coupled together via a bus system 604. It is understood that the bus system 604 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 604 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 6 Various buses are labeled as bus system 604 .

[0120] It is understood that memory 602 can be volatile memory or non-volatile memory, or can include both volatile and non-volatile memory. Non-volatile memory can include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disk, or compact disc read-only memory (CD-ROM); magnetic surface memory can include magnetic disk or tape storage. Volatile memory can include random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The memory 602 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0121] The memory 602 in the embodiment of the present invention is used to store various types of data to support the operation of the elastic fabric detection device 600. Examples of such data include any computer program for operating on the elastic fabric detection device 600. The program for implementing the method of the embodiment of the present invention may be included in the memory 602.

[0122] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 601. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or by software instructions. The above processor may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium located in a memory. The processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0123] In an exemplary embodiment, the elastic fabric detection device 600 can be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the above-mentioned method.

[0124] In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is merely a logical functional division. In actual implementation, other divisions may be employed, such as combining multiple units or components, integrating them into another system, or omitting or disabling certain features. Furthermore, the coupling, direct coupling, or communication connection between the components shown or discussed may be through interfaces. The indirect coupling or communication connection between devices or units may be electrical, mechanical, or other. The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of these units may be selected to achieve the objectives of the present embodiments based on actual needs. Furthermore, the functional units in the various embodiments of the present invention may all be integrated into a single processing module, each unit may be a separate unit, or two or more units may be integrated into a single unit. These integrated units may be implemented in hardware or as hardware plus software functional units.

[0125] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for detecting elastic fabric, characterized in that: Application to detection systems including elastic fabric sensor networks; The sensor is embedded in the elastic fabric; the detection method comprises: Establishing a first node and a second node of the elastic fabric sensor network; the first node includes the sensor; Acquire first data of the first node; encrypting the first data to obtain encrypted first data; Using the second node to perform ciphertext domain fusion processing on the encrypted first data to obtain a feature matrix of the elastic fabric; the feature matrix represents the correlation between the grid coordinates of the elastic fabric and the data of the sensor; The characteristic matrix is encrypted and sent to a terminal, so that the terminal decrypts the encrypted characteristic matrix and generates a test report of the elastic fabric; the test report is used to decide the use of the elastic fabric.

2. The detection method according to claim 1, characterized in that The sensor includes a temperature sensor and / or a pressure sensor; and obtaining the first data of the first node includes: When the elastic fabric is subjected to temperature and / or pressure, temperature data from the temperature sensor and / or pressure data from the pressure sensor are acquired.

3. The detection method according to claim 1, wherein The sensor further comprises a Bluetooth sensor; and the method further comprises: The unconfigured nodes in the elastic fabric sensor network are configured with the Bluetooth sensor.

4. The detection method according to claim 3, characterized in that The encrypting the first data to obtain the encrypted first data includes: The first data is mapped and then encrypted using a preset homomorphic encryption technology to obtain the encrypted first data.

5. The detection method according to claim 4, characterized in that The step of performing ciphertext domain fusion processing on the encrypted first data using the second node to obtain a feature matrix of the elastic fabric includes: Using the second node to obtain the state matrix, observation matrix, control matrix, and gain matrix of the encrypted first data; Multimodal data fusion is performed on the state matrix, the observation matrix, the control matrix, and the gain matrix to obtain a feature matrix of the elastic fabric.

6. The detection method according to claim 5, characterized in that The method further comprises: The dimension of the characteristic matrix is compressed to obtain a compressed characteristic matrix; the compressed characteristic matrix is encrypted and sent to the terminal.

7. The detection method according to any one of claims 1 to 6, characterized in that The method further comprises: Get the preset private key; Decrypting the encrypted characteristic matrix using the private key to obtain a decrypted characteristic matrix; A test report of the elastic fabric is generated based on the decrypted feature matrix.

8. The detection method according to claim 7, characterized in that The output end of the sensor is connected in parallel to an RC filter network; the method further comprises: When the elastic fabric is in an unloaded state, obtaining an output signal of the sensor; performing noise filtering on the output signal to obtain a digital signal corresponding to the output signal; Performing filtering on the digital signal to obtain a filtered digital signal; Noise compensation is performed on the filtered digital signal to obtain the first data.

9. A detection system for elastic fabrics, characterized in that: The detection system includes an elastic fabric, a temperature sensor and / or a pressure sensor, and a processing device; the temperature sensor and / or the pressure sensor are embedded in the elastic fabric; the temperature sensor and / or the pressure sensor form a sensor network; The temperature sensor is connected to the temperature sensor signal line; the pressure sensor is connected to the pressure sensor signal line; the processing device is connected to the temperature sensor signal line and the pressure sensor signal line respectively; wherein, The temperature sensor signal line is used to obtain temperature data of the temperature sensor when the elastic fabric is subjected to temperature; The pressure sensor signal line is used to obtain pressure data of the pressure sensor when the elastic fabric is under pressure; The processing device is used to encrypt the temperature data and / or the pressure data to obtain encrypted first data; perform ciphertext domain fusion processing on the encrypted first data to obtain a feature matrix of the elastic fabric; the feature matrix represents the association between the grid coordinates of the elastic fabric and the data of the sensor; the feature matrix is encrypted and sent to the terminal, so that the terminal decrypts the encrypted feature matrix and generates a test report of the elastic fabric; the test report is used to decide the use of the elastic fabric.

10. An elastic fabric detection device, characterized in that: The device comprises: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is configured to execute the steps of the detection method according to any one of claims 1 to 8 when running the computer program.

Images