Industrial equipment interpretable traceability system and method based on dynamic working spectrum resonance mapping and self-certification anti-counterfeiting

Abstract

The invention discloses an industrial equipment interpretable traceability system and method based on dynamic working spectrum resonance mapping and self-certification anti-counterfeiting. According to the system, multi-source operation signals of equipment are collected in real time, a dynamic working spectrum characteristic spectrum is constructed, key working condition fingerprints are extracted through a resonance mapping mechanism, and interpretable expression and traceability identification of the state of the equipment are achieved. And meanwhile, a block chain and a self-certification anti-counterfeiting mechanism are introduced, and encryption and evidence storage are performed on the working spectrum signature, so that the uniqueness and tamper resistance of the tracing data are ensured. The method can perform high-precision traceability analysis on the operation state, historical behaviors and abnormal events of the complex industrial equipment, has the advantages of high interpretability, high anti-counterfeiting performance, wide adaptability and the like, and is suitable for the fields of equipment manufacturing, energy monitoring, intelligent maintenance and the like.

Description

Technical Field

[0001] This invention belongs to the fields of Internet of Things and artificial intelligence technology, specifically relating to an interpretable traceability system and method for industrial equipment based on dynamic working spectrum resonance mapping and self-verification anti-counterfeiting. Background Technology

[0002] This invention relates to the fields of industrial equipment operation behavior detection, status identification, and reliable traceability technology, particularly focusing on dynamic feature modeling, self-verification and anti-counterfeiting of operation process data, and interpretable traceability technology for equipment operation data under complex operating conditions. With the advancement of the Industrial Internet, intelligent manufacturing, and digital factories, industrial equipment has gradually become a high-frequency, high-value core asset in the production system. The authenticity and traceability of equipment operation status are directly related to production safety, quality stability, and maintenance decisions. However, traditional equipment traceability methods mostly rely on static identification, factory codes, manual records, and simple log management, which cannot reflect the true behavioral characteristics of equipment during actual operation, lack in-depth analytical capabilities regarding the operation process, changes in operating conditions, and abnormal evolution paths, and cannot support the requirements of refined management and reliable security.

[0003] Existing industrial monitoring and traceability technologies still have significant shortcomings in signal processing, condition recognition, and data security. On the one hand, traditional signal analysis methods often focus on extracting local features in the time or frequency domains, making it difficult to characterize the dynamic coupling and evolution of multi-dimensional signals from equipment in the time-frequency space. Under complex operating conditions, multi-source signals such as equipment vibration, temperature, current, and acoustics exhibit high noise, nonlinearity, and time-varying characteristics. Traditional methods struggle to capture the relationship between operating condition fingerprints and dynamic pattern transitions, resulting in insufficient model interpretability and an inability to clearly trace the logic of equipment condition changes. On the other hand, although blockchain, edge computing, and industrial big data have been used in recent years to improve the credibility of industrial data, existing solutions generally rely on static production data and lack real-time hash fingerprint construction and self-verification anti-counterfeiting mechanisms for runtime data, failing to effectively guarantee the formation of a trustworthy data chain throughout the entire equipment lifecycle.

[0004] Therefore, there is an urgent need for an equipment traceability method that can integrate dynamic modeling of multi-source operating signals, time-frequency resonance feature analysis, and a reliable evidence storage mechanism to achieve the generation of equipment status fingerprints, the construction of operating condition correlation paths, and the self-verifying secure storage of operating data. This invention proposes an interpretable traceability system and method for industrial equipment based on dynamic operating spectrum resonance mapping and self-verifying anti-counterfeiting, aiming to provide an interpretable, verifiable, and traceable operating process recording mechanism for complex industrial equipment, and to provide fundamental technical support for intelligent manufacturing, equipment condition health management, and industrial safety and quality control. Summary of the Invention

[0005] To address the aforementioned issues, this invention discloses an interpretable traceability system and method for industrial equipment based on dynamic operating spectrum resonance mapping and self-verifying anti-counterfeiting. The system constructs a dynamic operating spectrum of the equipment by collecting multi-source operating signals, extracts operating condition fingerprints using frequency domain resonance analysis and time-series pattern correlation mechanisms, and establishes an interpretable correlation path between the equipment's operating status and historical operating conditions through an inter-spectral mapping model. This enables traceability analysis and behavioral logic expression of the equipment's operation process. Simultaneously, by combining hash digest, digital signature, and blockchain on-chain evidence storage technologies, the dynamic operating spectrum fingerprints and traceability records are self-verified, trusted, and tamper-proofed, thus forming a dynamic behavior record and trusted verification capability throughout the equipment's entire lifecycle. This method achieves dynamic modeling, interpretable tracking, and chain-based authentication of equipment operating status, and is applicable to scenarios such as intelligent manufacturing, equipment health management, and industrial safety monitoring.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0007] An interpretable traceability system and method for industrial equipment based on dynamic operating spectrum resonance mapping and self-verification anti-counterfeiting includes the following steps:

[0008] S1 collects vibration, acoustic, temperature, current, and voltage operating signals in real time through sensors deployed in key parts of industrial equipment; performs noise reduction, normalization, and time-frequency transformation on the raw signals to obtain multi-dimensional time-series characteristics; and constructs the dynamic operating spectrum of the equipment to describe the energy distribution and characteristic change process of the equipment under different operating conditions.

[0009] S2, frequency domain resonance analysis is performed on the dynamic working spectrum to establish resonance mapping relationship between working spectra; through multi-scale feature extraction and resonance response aggregation, key frequency bands and energy modes reflecting the equipment operating status are identified, forming a unique operating condition feature fingerprint, which serves as the basic data representation for traceability analysis;

[0010] S3. The extracted operating condition feature fingerprints are input into the traceability model and compared and mapped with the historical working spectrum database to generate the genealogical relationship corresponding to the equipment operating status. The association structure between the equipment operating trajectory, state sequence and corresponding operating condition features is established through a visual mapping mechanism to form an interpretable traceability path.

[0011] S4 performs hash encoding and encrypted signature processing on the working spectrum fingerprint, mapping results and traceability records generated during the traceability process; it encrypts and writes them into the blockchain distributed ledger to realize the on-chain registration and timestamp storage of data; and completes the verification and trusted management of traceability information through the self-certification anti-counterfeiting mechanism to realize the verifiability and continuous traceability of data records.

[0012] The dynamic operating spectrum of the device constructed in S1 is as follows:

[0013] S11, define x k (t) The time-domain signal acquired by the k-th sensor, k = 1, 2, ..., K, where K is the total number of signal channels and t is the time variable; after time synchronization and noise suppression, the signal matrix is ​​formed: X(t) = [x1(t), x2(t), ..., x K (t)] T ;

[0014] S12, for each signal x k (t) is subjected to Fourier transform to obtain its time-frequency energy distribution spectrum:

[0015]

[0016] Among them, S k (f,τ) is the complex spectrum of the k-th signal at frequency f and time window center τ, w(t-τ) is the window function used to control the local time domain range, f is the frequency variable (Hz), and j is the imaginary unit; the energy spectrum can be expressed as E k (f,τ)=|S k (f,τ)| 2 ;

[0017] S13, to comprehensively assess the ability of each channel to characterize the device status, a weighted fusion of the energy spectrum is performed:

[0018]

[0019] Where, α k It is the channel weight coefficient, which satisfies max(E k ) is the maximum energy of the k-th channel, and E(f,τ) represents the comprehensive energy distribution of the signal at different time and frequency points;

[0020] S14, to reflect the dynamic changes in the equipment's operating status over time, the time-varying rate of change of the energy spectrum is differentiated, and the dynamic operating spectrum of the equipment is defined as follows:

[0021]

[0022] in, It is the dynamic operating spectrum value of the device at frequency f and time τ. It is the time derivative of the energy spectrum.

[0023] The resonance mapping relationship between working spectra established in S2 is as follows:

[0024] S21, for the same device in two time slices τ p With τ q Dynamic working spectrum and Its frequency resonance response function is defined as:

[0025]

[0026] Wherein, R(f) i ,f j ;τ p ,τ q ) is the frequency f i with f j Between time windows τ p With τ q The resonance intensity below, The dynamic working spectrum amplitude corresponds to the frequency and time, where ε is a constant to prevent the denominator from being zero, f i ,f j ∈[f min ,f max ] is the frequency sampling point, τ p ,τ q ∈[τ1,τ N [] represents the time sampling window;

[0027] S22, calculate the resonance response function in the full frequency domain to obtain the resonance mapping matrix:

[0028]

[0029] Where R(τ) p ,τ q ) is the time window τ p With τ q The frequency domain resonance mapping matrix between them, where F is the number of frequency sampling points. This represents the energy coupling strength distribution between all frequency band pairs;

[0030] Energy aggregation and weighted averaging are performed on the resonance mapping matrices for each time window, and the global resonance spectrum is defined as follows:

[0031]

[0032] Where M is the total number of time windows, β pq These are time window weighting coefficients, satisfying ∑ p<q β pq =1;

[0033] S23, from the global resonance spectrum Extract the main resonance feature vectors and define the resonance feature fingerprint as follows:

[0034] F=[λ1,λ2,…,λ d ]

[0035] Where, λ i yes The i-th eigenvalue is arranged in descending order, and d is the selected resonance feature dimension.

[0036] The traceability model in S3 is as follows:

[0037] S31, the current device's resonance feature fingerprint is The historical database stores feature fingerprint samples under N different operating conditions. F ( n) Mapped to a unified interpretable feature space

[0038] z (n) =Φ(F (n) ),z (t) =Φ(F (t) )

[0039] Where Φ(·) is the feature embedding mapping function, z (n) z is the representation of the nth historical sample in the embedding space. (t) It is the representation of the current device state in the embedding space, where m is the dimension of the embedding feature space;

[0040] S32, the spectral similarity function is defined as follows:

[0041]

[0042] Among them, S tn is the similarity coefficient between the current spectrum and the nth historical spectrum, <·,·> is the vector inner product operator, and ||·||2 is the 2-norm;

[0043] S33, according to the similarity matrix A = [S tn ] t,n Construct a tracing genealogical association matrix:

[0044] G = S⊙M

[0045] in is the phylogenetic correlation matrix, ⊙ is the Hadamard product operator, M is the time series constraint matrix, and T is the number of time slices for the current device state;

[0046] Define a tracing path function based on the genealogy matrix G:

[0047]

[0048] Where Ψ(τ) t ) indicates the time window τ t The historical spectral index that matches it, G t,n It is a time window τ t The phylogenetic correlation strength with historical sample n is calculated sequentially for each time window, corresponding to Ψ(τ).t Generate genealogical tracing sequences during device operation.

[0049] The self-verifying anti-counterfeiting mechanism in S4 is as follows:

[0050] S41, the data generated during the equipment traceability process is uniformly encoded to form a data block to be stored:

[0051]

[0052] in It is a set of encoded traceable data, and Enc(·) is a data encoding or serialization function. It is the device's dynamic operating spectrum, and F is the resonance characteristic fingerprint. It traces the path sequence; for data blocks Perform hash digest operation to generate a unique identifier value. H(·) is a one-way hash function;

[0053] S42, Perform a digital signature operation on the digest h:

[0054] σ = Sign priv (h)

[0055] Where σ is the signature result, Sign priv (·) A function that signs a data digest using the private key priv; the corresponding public key pub is used for signature verification:

[0056]

[0057] S43, write the signature result and data digest together into the blockchain ledger to form a transaction data block:

[0058]

[0059] in, It is the i-th on-chain data block, h i It is the hash digest of the i-th trace record, σ i It corresponds to the signature value, t i It's the on-chain timestamp, addr i It is the blockchain address identifier of the device node, prev_hash i It is the hash value of the previous block; the chain structure satisfies the recursive relationship. To achieve chain-like association and irreversible time-series storage of traceable records;

[0060] S44, When it is necessary to verify a traceable record, the system uses the hash identifier h ′ Retrieve the corresponding block from the blockchain. Consistency is verified using the following relationship:

[0061] And Verify pub (h i ,σ i ) = 1

[0062] If all of the above conditions are met, it means that the data is complete and the source is reliable; otherwise, the record is deemed to have been tampered with and is invalid.

[0063] Compared with the prior art, the beneficial effects of this invention are:

[0064] (1) This invention constructs a dynamic operating spectrum of industrial equipment by collecting operating signals from multiple sources such as vibration, acoustics, current, and temperature, and extracts operating condition feature fingerprints based on the resonance response mechanism, thereby achieving a unified representation of the dynamic behavior of equipment under complex operating conditions. This method can describe the frequency domain coupling and energy evolution characteristics during equipment operation, providing interpretable analysis capabilities for the logic of equipment state changes, and solving the problem that traditional methods rely only on static indicators or local features and cannot characterize the true operating characteristics of equipment.

[0065] (2) This invention uses inter-spectral similarity calculation and a spectral association model to progressively map the current operating condition of equipment to its historical operating state, forming a spectral link of equipment state evolution, and realizing dynamic tracking of the entire process of equipment from normal operating condition, fluctuation changes to abnormal state. This traceability mechanism allows the equipment operation process to be presented hierarchically and sequentially, which helps to clearly restore the equipment's operating trajectory, operating condition change logic and corresponding temporal relationship, and improves the information transparency and management accuracy of operation management.

[0066] (3) This invention utilizes hash digests, digital signatures, and blockchain technology to uniquely identify and chain-record dynamic working spectrum fingerprints and traceability paths, thereby establishing a trusted link for the entire process of equipment operation data from collection and processing to traceability. This mechanism ensures that equipment operation information is tamper-proof, verifiable, and traceable, effectively improving the security and trustworthiness of industrial equipment data transmission and sharing processes, and providing solid support for auditing, liability identification, and trusted supervision of industrial production processes. Attached Figure Description

[0067] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0068] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0069] Figure 1 This is a flowchart of an embodiment of the present invention. Detailed Implementation

[0070] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. These descriptions are only for further illustrating the features and advantages of the present invention, and not for limiting the claims of the present invention. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0071] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0072] like Figure 1 As shown, the framework of this invention mainly consists of the following four steps, which are connected layer by layer and ultimately merged. The process mainly includes the following steps:

[0073] S1 collects vibration, acoustic, temperature, current, and voltage operating signals in real time through sensors deployed in key parts of industrial equipment; performs noise reduction, normalization, and time-frequency transformation on the raw signals to obtain multi-dimensional time-series characteristics; and constructs the dynamic operating spectrum of the equipment to describe the energy distribution and characteristic change process of the equipment under different operating conditions.

[0074] The dynamic operating spectrum of the device constructed in S1 is as follows:

[0075] S11, define x k (t) The time-domain signal acquired by the k-th sensor, k = 1, 2, ..., K, where K is the total number of signal channels and t is the time variable; after time synchronization and noise suppression, the signal matrix is ​​formed: X(t) = [x1(t), x2(t), ..., x K (t)] T ;

[0076] S12, for each signal x k(t) is subjected to Fourier transform to obtain its time-frequency energy distribution spectrum:

[0077]

[0078] Among them, S k (f,τ) is the complex spectrum of the k-th signal at frequency f and time window center τ, w(t-τ) is the window function used to control the local time domain range, f is the frequency variable (Hz), and j is the imaginary unit; the energy spectrum can be expressed as E k (f,τ)=|S k (f,τ)| 2 ;

[0079] S13, to comprehensively assess the ability of each channel to characterize the device status, a weighted fusion of the energy spectrum is performed:

[0080]

[0081] Where, α k It is the channel weight coefficient, which satisfies max(E k ) is the maximum energy of the k-th channel, and E(f,τ) represents the comprehensive energy distribution of the signal at different time and frequency points;

[0082] S14, to reflect the dynamic changes in the equipment's operating status over time, the time-varying rate of change of the energy spectrum is differentiated, and the dynamic operating spectrum of the equipment is defined as follows:

[0083]

[0084] in, It is the dynamic operating spectrum value of the device at frequency f and time τ. It is the time derivative of the energy spectrum.

[0085] S2, frequency domain resonance analysis is performed on the dynamic working spectrum to establish resonance mapping relationship between working spectra; through multi-scale feature extraction and resonance response aggregation, key frequency bands and energy modes reflecting the equipment operating status are identified, forming a unique operating condition feature fingerprint, which serves as the basic data representation for traceability analysis;

[0086] The resonance mapping relationship between working spectra established in S2 is as follows:

[0087] S21, for the same device in two time slices τ p With τ q Dynamic working spectrum and Its frequency resonance response function is defined as:

[0088]

[0089] Wherein, R(f) i ,f j ;τ p ,τ q ) is the frequency f i with f j Between time windows τ p With τ q The resonance intensity below, The dynamic working spectrum amplitude corresponds to the frequency and time, where ε is a constant to prevent the denominator from being zero, f i ,f j ∈[f min ,f max ] is the frequency sampling point, τ p ,τ q ∈[τ1,τ N [] represents the time sampling window;

[0090] S22, calculate the resonance response function in the full frequency domain to obtain the resonance mapping matrix:

[0091]

[0092] Where R(τ) p ,τ q ) is the time window τ p With τ q The frequency domain resonance mapping matrix between them, where F is the number of frequency sampling points. This represents the energy coupling strength distribution between all frequency band pairs;

[0093] Energy aggregation and weighted averaging are performed on the resonance mapping matrices for each time window, and the global resonance spectrum is defined as follows:

[0094]

[0095] Where M is the total number of time windows, β pq These are time window weighting coefficients, satisfying ∑ p<q β pq =1;

[0096] S23, from the global resonance spectrum Extract the main resonance feature vectors and define the resonance feature fingerprint as follows:

[0097] F=[λ1,λ2,…,λ d ]

[0098] Where, λ i yes The i-th eigenvalue is arranged in descending order, and d is the selected resonance feature dimension.

[0099] S3. The extracted operating condition feature fingerprints are input into the traceability model and compared and mapped with the historical working spectrum database to generate the genealogical relationship corresponding to the equipment operating status. The association structure between the equipment operating trajectory, state sequence and corresponding operating condition features is established through a visual mapping mechanism to form an interpretable traceability path.

[0100] The traceability model in S3 is as follows:

[0101] S31, the current device's resonance feature fingerprint is The historical database stores feature fingerprint samples under N different operating conditions. F ( n) Mapped to a unified interpretable feature space

[0102] z (n) =Φ(F (n) ),z (t) =Φ(F (t) )

[0103] Where Φ(·) is the feature embedding mapping function, z (n) z is the representation of the nth historical sample in the embedding space. (t) It is the representation of the current device state in the embedding space, where m is the dimension of the embedding feature space;

[0104] S32, the spectral similarity function is defined as follows:

[0105]

[0106] Among them, S tn is the similarity coefficient between the current spectrum and the nth historical spectrum, <·,·> is the vector inner product operator, and ||·||2 is the 2-norm;

[0107] S33, according to the similarity matrix S = [S tn ] t,n Construct a tracing genealogical association matrix:

[0108] G = S⊙M

[0109] in is the phylogenetic correlation matrix, ⊙ is the Hadamard product operator, M is the time series constraint matrix, and T is the number of time slices for the current device state;

[0110] Define a tracing path function based on the genealogy matrix G:

[0111]

[0112] Where Ψ(τ) t ) indicates the time window τ tThe historical spectral index that matches it, G t,n It is a time window τ t The phylogenetic correlation strength with historical sample n is calculated sequentially for each time window, corresponding to Ψ(τ). t Generate genealogical tracing sequences during device operation.

[0113] S4 performs hash encoding and encrypted signature processing on the working spectrum fingerprint, mapping results and traceability records generated during the traceability process; it encrypts and writes them into the blockchain distributed ledger to realize the on-chain registration and timestamp storage of data; and completes the verification and trusted management of traceability information through the self-certification anti-counterfeiting mechanism to realize the verifiability and continuous traceability of data records.

[0114] The self-verifying anti-counterfeiting mechanism in S4 is as follows:

[0115] S41, the data generated during the equipment traceability process is uniformly encoded to form a data block to be stored:

[0116]

[0117] in It is a set of encoded traceable data, and Enc(·) is a data encoding or serialization function. It is the device's dynamic operating spectrum, and F is the resonance characteristic fingerprint. It traces the path sequence; for data blocks Perform hash digest operation to generate a unique identifier value. H(·) is a one-way hash function;

[0118] S42, Perform a digital signature operation on the digest h:

[0119] σ = Sign priv (h)

[0120] Where σ is the signature result, Sign priv (·) A function that signs a data digest using the private key priv; the corresponding public key pub is used for signature verification:

[0121]

[0122] S43, write the signature result and data digest together into the blockchain ledger to form a transaction data block:

[0123]

[0124] in, It is the i-th on-chain data block, h i It is the hash digest of the i-th trace record, σ i It corresponds to the signature value, t iIt's the on-chain timestamp, addr i It is the blockchain address identifier of the device node, prev_hash i It is the hash value of the previous block; the chain structure satisfies the recursive relationship. To achieve chain-like association and irreversible time-series storage of traceable records;

[0125] S44, When it is necessary to verify a traceable record, the system uses the hash identifier h ′ Retrieve the corresponding block from the blockchain. Consistency is verified using the following relationship:

[0126] And Verify pub (h i ,σ i ) = 1

[0127] If all of the above conditions are met, it means that the data is complete and the source is reliable; otherwise, the record is deemed to have been tampered with and is invalid.

[0128] This invention utilizes mechanisms such as dynamic operating spectrum construction, resonance fingerprint extraction, and spectral mapping tracing to achieve dynamic identification and interpretable correlation modeling of the entire process of industrial equipment operation status. This allows for a clear presentation of the energy evolution patterns and operational mode change paths of the equipment under different operating conditions. Simultaneously, by leveraging hash digest, digital signature, and blockchain notarization technologies, it provides trusted identification and tamper-proof guarantees for operational data and traceability records, thereby forming a trusted operational archive spanning the entire equipment lifecycle. After applying this invention, normal operating conditions, transitional states, and abnormal behaviors during industrial equipment operation can all be presented in a structured, visualized, and verifiable manner. This facilitates management personnel in verifying equipment operating logic, tracking key events, and determining responsibility boundaries. It is applicable to various scenarios such as intelligent manufacturing equipment management, process quality supervision, operation and maintenance health management, and industrial safety auditing.

[0129] The above description only illustrates the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention, and all such changes should be included within the protection scope of the present invention.

Claims

1. An industrial equipment interpretable traceability system and method based on dynamic work profile resonance mapping and self-certified anti-counterfeiting, characterized in that, Comprise the following steps: S1, through the sensor deployed in the key parts of industrial equipment, real-time acquisition of vibration, acoustic, temperature, current, voltage operation signal; the original signal is denoised, normalized and time-frequency transform processing, obtains multi-dimensional time sequence characteristics; Construct the dynamic working spectrum of the device, describe the energy distribution and characteristic change process of the device under different working conditions; S2, frequency domain resonance analysis is carried out on the dynamic working spectrum, and the resonance mapping relationship between the working spectrums is established; Through multi-scale feature extraction and resonance response aggregation, the key frequency band and energy mode reflecting the running state of the equipment are identified, and a unique working condition characteristic fingerprint is formed, which is used as the basic data representation of traceability analysis; S3, the working condition characteristic fingerprint extracted is input into the traceability model, compared and associated with the historical working spectrum database, and the spectrum relationship corresponding to the running state of the equipment is generated; Through the visual mapping mechanism, the correlation structure between the running track, state sequence and corresponding working condition characteristics of the equipment is established, and an interpretable traceability path is formed; S4, the working spectrum fingerprint, mapping result and traceability record generated in the traceability process are processed by hash coding and encryption signature; Write into the blockchain distributed ledger, realize the on-chain registration and time stamp of data; Through the self-authentication anti-fake mechanism, the verification and credible management of traceability information are completed, and the verifiability and continuous traceability of data record are realized.

2. A dynamic duty spectrum resonance mapping and self-authenticating anti-counterfeit based industrial equipment interpretable traceability system and method according to claim 1, characterized in that, The dynamic working spectrum of the device constructed in S1 is: S11, define x k (t) the time domain signal collected by the kth sensor, k = 1, 2, …, K, K is the total number of signal channels, t is the time variable; after time synchronization and noise suppression, the signal forms a signal matrix: X(t) = [x1(t), x2(t), …, xK(t)] K (t)] T ; S12, for each signal x k (t) Fourier transform is performed to obtain its time-frequency energy distribution spectrum: where S k (f,τ) is the complex-valued spectrum of the kth signal at frequency f and time window center τ, w(t - τ) is a window function used to control the local time domain range, f is the frequency variable (Hz), and j is the imaginary unit; the energy spectrum can be expressed as E k (f,τ) = |S k (f,τ)| 2 ; S13, for comprehensive representation of the state of the device, the energy spectrum is weighted and fused: wherein α k is a channel weight coefficient satisfying max(E k ) is the maximum energy of the kth channel, and E(f, τ) represents the overall energy distribution of the signal at different time-frequency points. S14, for reflecting the dynamic change of the running state of the device with time, the time variation rate of the energy spectrum is derived, and the dynamic working spectrum of the device is defined as wherein, is the dynamic operating spectrum value of the device at frequency f and time τ, is the time derivative of the energy spectrum.

3. A system and method for interpretable traceability of industrial equipment based on dynamic working spectrum resonance mapping and self-certified anti-counterfeiting according to claim 2, characterized in that, The resonance mapping relationship between the working spectrums in S2 is: S21, for the same device at two time slices τ p and τ q under dynamic working profile and defined its frequency resonance response function as: Wherein, R(f) i ,f j ;τ p ,τ q ) is the frequency f i with f j Between time windows τ p With τ q The resonance intensity below, The dynamic working spectrum amplitude corresponds to the frequency and time, where ε is a constant to prevent the denominator from being zero, f i ,f j ∈[f min ,f max ] is the frequency sampling point, τ p ,τ q ∈[τ1,τ N [] represents the time sampling window; S22, the resonance response function is calculated in the full frequency domain, and the resonance mapping matrix is obtained: where R(τ q ,τ q ) is the frequency domain resonance mapping matrix between time windows τ q and τ q , F is the number of frequency samples, is a representation of the distribution of the strength of the energy coupling between all pairs of frequency bands; The energy aggregation and weighted average of the resonance mapping matrix of each time window are carried out, and the global resonance spectrum is defined as: where m is the total number of time windows, β pq is the time window weight coefficient, satisfying p<q β pq = 1; S23, extracting main resonance feature vectors from the global resonance spectrum and defining the resonance feature fingerprint as: F = [λ1, λ2,..., λ d ] where λ i is the i-th eigenvalue of the Laplacian matrix L, sorted in descending order, and d is the selected dimension of the resonant features.

4. A system and method for interpretable traceability of industrial equipment based on dynamic working spectrum resonance mapping and self-certified anti-counterfeiting according to claim 3, characterized in that, The traceability model in S3 is: S31, the resonance feature fingerprint of the current device is The feature fingerprint samples in the historical database under N different working conditions are stored F ( n) mapped to a unified interpretable feature space z (n) = Φ(F (n) ),z (t) = Φ(F (t) ) where Φ(·) is a feature embedding mapping function, z (n) is the representation of the nth historical sample in the embedding space, z (t) is the representation of the current device state in the embedding space, m is the dimension of the embedding feature space; S32, define the similarity function between spectrums as: where S tn is the similarity coefficient between the current spectrum and the nth historical spectrum, <·, ·> is the vector inner product operator, and ||·||2 is the two-norm. S33, constructing a traceable pedigree correlation matrix S according to the similarity matrix S = [S tn ] t,n , constructing a traceable pedigree correlation matrix: G=S⊙M wherein is a lineage association matrix, is a Hadamard product operator, M is a time series constraint matrix, and T is the number of time slices of the current device state; Based on the spectrum matrix G, define the traceability path function: where Ψ(τ t ) represents the historical spectrum index matched with the time window τ t , G t,n is the spectrum-based correlation strength of the time window τ t and the historical sample n, and Ψ(τ t ) is calculated in turn to generate the spectrum-based lineage tracking sequence in the device running process 5. A system and method for interpretable traceability of industrial equipment based on dynamic working spectrum resonance mapping and self-certified anti-counterfeiting according to claim 4, characterized in that, The self-authentication anti-fake mechanism in S4 is: S41, the data generated in the process of equipment traceability is uniformly coded to form a data block to be notarized: wherein is the encoded trace data set, Enc(·) is a data encoding or serialization function, is the device dynamic work profile, F is the resonance signature fingerprint, is the trace path sequence; a hash digest operation is performed on the data block to generate a unique identification value H(·) is a one-way hash function; S42, the digital signature operation is carried out on the digest h: σ = Sign priv (h) where σ is the signature result, Sign priv (·) a function that signs a data digest with a private key priv; the corresponding public key pub is used for signature verification: S43, the signature result and the data digest are written into the blockchain ledger to form a transaction data block: wherein, is the i-th upper chain data block, h i is the hash digest of the i-th trace record, σ i is the corresponding signature value, t i is the on-chain timestamp, addr i is the blockchain address identification of the device node, prev_hash i is the hash value of the previous block; the chain structure satisfies the recursive relationship The chain association and irreversible time sequence storage of the trace record are realized. S44, when a certain trace record needs to be verified, the system verifies the trace record according to the hash identifier h ′ retrieving the corresponding block from the blockchain consistency is verified by the following relationship: and Verify pub (h i ,σ i ) = 1 If the above conditions are met at the same time, it means that the data is complete and the source is credible; Otherwise, it is determined that the record is tampered and invalid.

Images