A privacy protection method for industrial data transmission

Abstract

The present invention discloses a privacy protection method for industrial data transmission. The method comprises the following steps: first, obtaining industrial data and performing localized processing; distributing the localized industrial data to a number of clients; constructing a local fully-connected neural network on the client, and using the distributed industrial data to train the local fully-connected neural network to obtain optimal model parameters; encrypting the optimal parameters obtained through training using homomorphic encryption; each client transmits the encrypted optimal parameters to a central server; the central server applies an adaptive model aggregation strategy to dynamically weighted aggregate the model parameter data uploaded by each client to obtain a global fully-connected neural network; applying the aggregated global fully-connected neural network to predict the industrial data, and simultaneously transmitting the model parameters of the global fully-connected neural network to each client; and the client uses the transmitted model parameters to adjust the training frequency and dynamically update the local local fully-connected neural network.

Description

Technical Field

[0001] The present invention relates to the field of data security technology, and in particular to a privacy protection method for industrial data transmission. Background Art

[0002] With the development of the Industrial Internet, the collection and processing of industrial data has become a core component of intelligent manufacturing and industrial optimization. However, industrial data often contains a large amount of sensitive information, including equipment status during production, product quality monitoring, and personnel behavior data. Protecting the privacy of this data has become a major challenge in the current digital transformation of industry.

[0003] Traditional industrial data transmission and processing requires data to be transmitted over public networks and typically stored on centralized servers, exposing it to security risks such as data leakage, tampering, and misuse. Existing privacy protection technologies primarily focus on encrypted transmission and data anonymization, but these technologies still cannot effectively resolve the conflict between data privacy, data quality, and model optimization.

[0004] To address this issue, distributed training using federated learning has become an ideal solution. Federated learning allows each client to train models locally without uploading raw data to a central server, thus protecting data privacy. However, existing federated learning frameworks still have some issues, such as the risk of privacy leakage during model training, variations in client data quality, and the inefficient aggregation of model parameters.

[0005] Therefore, how to improve the quality of industrial data and optimize the efficiency of global model training while ensuring data privacy has become a technical problem that needs to be solved urgently. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this paper proposes a privacy-preserving method for industrial data transmission based on an adaptive timing window strategy, intelligent noise removal, encrypted transmission, and a privacy-preserving authentication mechanism. This method not only ensures the privacy and security of industrial data during transmission but also improves data quality and global model training, thereby promoting industrial intelligence and data-driven optimization applications.

[0007] In order to solve the above technical problems, the technical solution of the present invention is:

[0008] A privacy protection method for industrial data transmission includes the following steps:

[0009] Step 1: Obtain industrial data and perform local processing. Specific methods include:

[0010] Adaptive Time Series Windowing Strategy: The client dynamically adjusts the size of the data aggregation window based on data volatility and autocorrelation. When data volatility is high, a smaller window is used to capture transient changes; when data volatility is low, a larger window is used for data smoothing.

[0011] Specifically, volatility is calculated by calculating the standard deviation σ of the data within the time period t , autocorrelation is calculated by calculating the autocorrelation coefficient ρ of the data t To measure. The formula for adjusting the window size is:

[0012] ω(t)=α·σ t +β·ρ t

[0013] Among them, α and β are adjustment factors, ω(t) is the dynamically changing window size, σ t is the standard deviation used to measure volatility, ρ t is the autocorrelation coefficient used to measure autocorrelation.

[0014] Intelligent noise detection and removal: Use a combination of wavelet transform and local statistics to remove noise from data.

[0015] Wavelet transform is used to extract the high-frequency noise component X of the data high , and remove these noises, retaining only the low-frequency valid data X low , the specific formula is:

[0016] X denoised =WT -1 (WT(X)·1 |WT(X)|＞θ )

[0017] Among them, X denoised is the data after denoising, WT(X) is the wavelet transform, θ is the retained noise threshold, 1 |WT(X)|＞θ is the threshold function;

[0018] By using local statistics, we can calculate the local mean and local variance of the data points to further determine the abnormal noise in the data. The specific formula is:

[0019]

[0020] Among them, μ local (x i ) is the local mean, σ local (x i ) is the local variance, and k is the neighbor window size.

[0021] Data cleaning based on quality score: During the data cleaning process, the client calculates the quality score Q(x i), and set the threshold, when the quality score Q(x i ) is less than the threshold, it is judged as low-quality data (Q(x i ) < 0.7), it is marked and removed. This ensures that the quality score of the data item takes into account the completeness, correctness and consistency of the data. The formula is as follows:

[0022] Q(x i )=ω com ·C(x i )+ω corr ·R(x i )+ω cons ·I(x i )

[0023] Among them, C(x i ) is the integrity score of the data, R(x i ) is the accuracy score of the data, I(x i ) is the consistency score of the data, ω com is the weight of data integrity score, ω corr is the weight of the data correctness score, ω cons The weight of the data consistency score. Low-quality data will be removed to ensure that the data uploaded to the central server can improve the training effect of the global model;

[0024] Step 2: Distribute the localized data to several clients: The localized data is distributed based on the number of clients. Each client receives a portion of the data allocated to it and uses this data for model training.

[0025] Step 3: Build a local fully connected neural network on the client: A local fully connected neural network is built on each client, using a privacy-preserving multilayer perceptron (MLP) model. The local network is trained using local data to obtain optimal model parameters. During training, the mean squared error (MSE) is used as the loss function, and the model parameters are updated based on backpropagation and optimization algorithms (such as the Adam optimizer). Differential privacy mechanisms are also applied, protecting client data privacy by adding Laplace noise.

[0026] Step 4: Use homomorphic encryption to encrypt the optimal parameters obtained through training: Each client will homomorphically encrypt the optimal model parameters obtained through training to ensure the privacy of the model parameters during transmission. The encrypted data is protected during transmission, thereby preventing man-in-the-middle attacks and data leakage;

[0027] Step 5. Each client transmits the encrypted data to the central server: The client uploads the encrypted model parameters to the central server to ensure the security and integrity of the data during transmission;

[0028] Step 6: The central server decrypts the model parameters and applies an adaptive model aggregation strategy for weighted aggregation: After receiving the encrypted data uploaded by all clients, the central server decrypts it using the server private key. Then, it uses the adaptive model aggregation strategy to dynamically weight the model parameters uploaded by each client to obtain a global fully connected neural network model. The aggregation strategy is weighted based on the data quality score of each client to ensure that high-quality clients contribute more to the global model and to prevent low-quality data from adversely affecting the model.

[0029] Step 7: Apply the aggregated global model for prediction and download model parameters for update: After the global model training is complete, the central server applies the aggregated global fully connected neural network to predict the industrial data and transmits the prediction results to the client. At the same time, the parameters of the global model are downloaded to each client for local model update and optimization.

[0030] Step 8: The client applies the downloaded model parameters to adjust the training frequency and dynamically update them. This adjustment primarily uses data quality scores to control how often clients participate in training. High-quality data allows clients to participate in more training rounds. The dynamic update strategy primarily uses model accuracy differences to control the client's contribution to the global model. Clients with higher accuracy contribute more to the global model.

[0031] The present invention has the following characteristics and beneficial effects:

[0032] This technical solution avoids direct data transmission by transmitting model parameters obtained by training a local, fully connected neural network on local data. This protects local data privacy and prevents local data loss. The central server's global, fully connected neural network applies the model parameters uploaded by the local client to predict local industrial data. Furthermore, to ensure the accuracy of the global, fully connected neural network's predictions of local industrial data, low-quality local data is first cleaned on the client side. The central server then uses an aggregation strategy to weight each client's data quality score, ensuring that higher-quality clients contribute more to the global model and preventing negative impacts from low-quality data. Finally, the training frequency is adjusted based on the data quality score to control the frequency of client training. High-quality data encourages clients to participate in more training rounds. A dynamic update strategy also controls the client's contribution to the global model based on model accuracy differences. Clients with higher accuracy contribute more to the global model, effectively improving the accuracy of the central server's industrial data predictions. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 This is a flowchart of the industrial data privacy protection method provided in this embodiment.

[0035] Figure 2 This is a flowchart of the local data preprocessing provided in this embodiment.

[0036] Figure 3 This is a flowchart of the model parameter encryption process provided in this embodiment.

[0037] Figure 4 This is a flowchart of the adaptive model aggregation process provided in this embodiment.

[0038] Figure 5 This is a flow chart for the dynamic update of the local fully connected neural network model provided in this embodiment. DETAILED DESCRIPTION

[0039] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0040] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings.

[0041] On the contrary, the present invention covers any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention as defined by the claims. Furthermore, to facilitate a better understanding of the present invention, certain specific details are described in detail below in the detailed description of the present invention. Those skilled in the art will be able to fully understand the present invention without these details.

[0042] In view of the limitations and deficiencies of existing technologies in protecting the privacy of industrial data transmission, this invention proposes an innovative solution. The following are specific embodiments:

[0043] This embodiment provides a flowchart of a privacy protection method for industrial data transmission, such as Figure 1 As shown, the method includes the following steps:

[0044] S1. Obtain industrial data and perform local processing

[0045] Specifically, localized processing methods include: adaptive timing window strategy, intelligent noise detection and removal, and cleaning methods based on data quality scoring, ensuring that the data uploaded by the client improves data quality while protecting privacy. Figure 2 As shown, the sub-steps of step S1 are as follows:

[0046] S1-1, Adaptive Timing Window Strategy

[0047] The client dynamically adjusts the data aggregation window based on the volatility and autocorrelation of industrial data. When data volatility is high, a smaller window is used to capture instantaneous changes; when data volatility is low, a larger window is used for data smoothing.

[0048] It should be noted that:

[0049] Small volatility: σ t ∈[0, 1], the data changes smoothly, and it is suitable to use a larger window to smooth the data;

[0050] Medium volatility: σ t ∈[1, 2], the data has moderate fluctuations and is suitable for using a medium-sized window;

[0051] Large volatility: σ t ∈[2, 3], the data changes dramatically, and it is suitable to use a smaller window to quickly respond to changes.

[0052] Calculation of volatility and autocorrelation: For each time period data X t , by calculating its standard deviation σt and autocorrelation ρ t To determine the window size:

[0053] First, the data client quantifies volatility by calculating the standard deviation of the data within a time window.

[0054]

[0055] Among them, σ t is the standard deviation of the data in time period t, X t-i Represents the data in the time series, μ t is the mean value for this period.

[0056] The correlation of the data is then measured by autocorrelation, which is calculated using the following formula:

[0057]

[0058] Among them, ρ t represents the autocorrelation of the data in time period t.

[0059] The window size is dynamically adjusted based on the data volatility and autocorrelation to ensure that both the smoothness and instantaneous changes of the data can be properly captured. The window size adjustment formula is:

[0060] ω(t)=α·σ t +β·ρ t

[0061] Among them, α and β are adjustment factors, ω(t) is the dynamically changing window size, σ t is the standard deviation used to measure volatility, ρ t is the autocorrelation coefficient used to measure autocorrelation.

[0062] S1-2. Intelligent noise removal method combining wavelet transform and local statistics

[0063] Wavelet transform denoising:

[0064] The data is decomposed by wavelet transform, and the high-frequency noise components are extracted and removed. For each time period signal X, the low-frequency component X is extracted after wavelet transform. low and high frequency noise X high :

[0065] X denoised =WT -1 (WT(X)·1 |WT(X)|＞θ )

[0066] Among them, X denoisedis the data after denoising, WT(X) is the wavelet transform, θ is the retained noise threshold, 1 |WT(X)|＞θ is the threshold function;

[0067] Local statistics assist in judgment:

[0068] By calculating the data point x i The local mean μ in the neighborhood local (x i ) and local variance σ local (x i ), further judge and remove abnormal noise.

[0069]

[0070] Among them, μ local (x i ) is the local mean, σ local (x i ) is the local variance, and k is the neighbor window size.

[0071] S1-3. Data cleaning method based on quality scoring:

[0072] Calculation of quality score: During the local cleaning process, the client will score the data quality based on the completeness, correctness and consistency of the data. The quality score Q(x i ) is calculated by the following formula:

[0073] Q(x i )=ω com ·C(x i )+ω corr ·R(x i )+ω cons ·I(x i )

[0074] Where: C(x i ) represents the integrity score of the data, R(x i ) represents the accuracy score of the data, I(x i ) represents the internal consistency score of the data, ω com is the weight of data integrity score, ω corr is the weight of the data correctness score, ω cons The weight of the data consistency score. The client removes low-quality data based on the quality score. Specifically, by setting a threshold, when the quality score Q(x i ) is less than the threshold, it is determined to be low-quality data, marked and removed to ensure that the uploaded data has a high contribution to the global model. In this embodiment, the threshold is set to 0.7. When Q(x i )<0.7 were evaluated as low-quality data.

[0075] S2. Distribute the localized data to several clients

[0076] In this embodiment, the localized data is evenly distributed based on the number of clients. Each client receives a portion of the data allocated to it and uses this data for model training.

[0077] S3. Build a local fully connected neural network on the client

[0078] Build a local fully connected neural network on each client.

[0079] Specifically, this embodiment adopts a privacy protection model based on a multi-layer perceptron (MLP), which receives industrial data features through the input layer. The hidden layer uses an activation function (ReLU) to extract deep features, and combines Dropout regularization and L2 regularization to prevent overfitting. The local network is trained using local data to obtain the optimal model parameters. During the training process, the mean square error (MSE) is used as the loss function, and the model parameters are updated based on the backpropagation algorithm and optimization algorithm (such as the Adam optimizer). At the same time, the differential privacy mechanism is applied to protect the privacy of client data by adding Laplace noise. The specific formula is as follows:

[0080]

[0081] Among them, g is the original gradient, It means that 0 is the mean, is the Laplace noise of the scale parameter, Δ is the sensitivity, and ∈ is the privacy budget.

[0082] S4. Use homomorphic encryption to encrypt the optimal parameters obtained through training.

[0083] The client encrypts the trained model parameters using homomorphic encryption technology, ensuring that even if the central server receives the encrypted parameters, it cannot decrypt and obtain the original data. The encryption process is set as follows:

[0084] Enc(ω i )=ε hom (ω i )

[0085] where ω i is the model parameter uploaded by the client, ε hom is a homomorphic encryption function.

[0086] S5. Each client transmits the encrypted data to the central server

[0087] The client uploads the encrypted model parameters to the central server to ensure the security and integrity of the data during transmission.

[0088] Specifically, such as Figure 3 As shown in Figure 2, the client's local model parameters are uploaded to the central server after being homomorphically encrypted.

[0089] S6. The central server decrypts the model parameters and applies the adaptive model aggregation strategy for weighted aggregation.

[0090] After receiving the encrypted data uploaded by all clients, the central server decrypts it using the server private key, and then uses the adaptive model aggregation strategy to dynamically weight and aggregate the model parameters uploaded by each client to obtain a global fully connected neural network model. The adaptive aggregation strategy is weighted based on the data quality score of each client to ensure that high-quality clients contribute more to the global model and avoid the adverse effects of low-quality data on the model, such as Figure 4 As shown, the sub-steps of step S6 are as follows:

[0091] S6-1. Decryption of model parameters

[0092] Use the server's private decryption key k dec Enc(ω i ) to decrypt and restore the model parameters ω i , the specific formula is as follows:

[0093] ω i =D hom (Enc(ω i ), k dec )

[0094] where ω i The model parameters uploaded by the client, D hom is the homomorphic decryption function.

[0095] S6-2. Weighted aggregation based on data quality

[0096] The quality score is calculated based on the model parameters of each client. The specific formula is as follows:

[0097] Q′(x i )=ω′ com ·C(x i )+ω′ corr ·R(x i )+ω′ cons ·I(x i )

[0098] Among them, Q′(x i ) is the quality score of each client model parameter, C(xi ) is the integrity score of the data, R(x i ) is the accuracy score of the data, I(x i ) is the consistency score of the data, ω′ com is the weight of data integrity score, ω′ corr is the weight of the data correctness score, ω′ cons The weight with which to score the data consistency.

[0099] According to the quality score Q′(x i ), assign different weights to the uploaded model parameters, and the model parameter aggregation formula is:

[0100]

[0101] Where N is the number of clients, ω logal is the aggregate weight of the global fully connected neural network, ω i Model parameters uploaded by the client.

[0102] S6-3. Model parameter weight adjustment of local fully connected neural network for low-quality clients

[0103] When the quality score Q′(x i ) is less than the threshold, it is determined to be low-quality data and assigned a low weight. In this embodiment, the threshold is set to 0.7. When Q′(x i ) < 0.7 is considered low-quality data. The model weights are adjusted using a linear attenuation formula to ensure that the negative impact of low-quality model parameter data on the global model is minimized. The specific adjustment formula is as follows:

[0104] ω′ i =γ·Q′(x i )·ω i

[0105] Among them, ω i is the model parameter weight uploaded by the original client, ω′ i is the adjusted client model weight, Q′(x i ) is the quality score of the model parameter data, and γ is the weight decay factor used to linearly adjust the weight range of low-quality clients. In this embodiment, γ is set to [0.5, 1.0].

[0106] S7: Apply the aggregated global model to make predictions and download model parameters for updating

[0107] After the global model training is completed, the central server uses the aggregated global fully connected neural network to predict the industrial data and transmit the prediction results to the client. At the same time, the parameters of the global model are transmitted to each client for updating and optimizing the local model.

[0108] S8, client application downloads model parameters for training frequency adjustment and dynamic update

[0109] like Figure 5 As shown, the sub-steps of step S8 are as follows:

[0110] S8-1. Training frequency adjustment: Dynamically adjust the frequency of each client's participation in model training based on its local data quality score. For example, clients with high data quality will be allowed to participate in model training more frequently. The specific formula is as follows:

[0111] f i =f base ·(1+α·Q′(x i ))

[0112] Among them, f i is the training frequency of client i, f base is the basic training frequency, and α is the adjustment coefficient.

[0113] S8-2. Dynamic update of training strategy: Based on the accuracy difference between the local model and the global model during training, the training strategy of each client is dynamically adjusted so that the global model achieves optimal performance while ensuring privacy. The specific formula is as follows:

[0114]

[0115] Where Δw i (t) is the model parameter update amount of the client at time t, λ is the learning rate adjustment factor, and accuracy i (t)-accuracy global (t) is the accuracy gap between the local model of client i and the global model.

[0116] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions, and variations of these embodiments, including components, without departing from the principles and spirit of the present invention are still within the scope of protection of the present invention.

Claims

1. A privacy protection method for industrial data transmission, characterized in that: The steps include: Step 1: Obtain industrial data and perform local processing; Step 2: Distribute the localized industrial data to several clients; Step 3: Build a local fully connected neural network on the client and use the allocated industrial data to train the local fully connected neural network to obtain the optimal model parameters; Step 4: Use homomorphic encryption to encrypt the optimal parameters obtained through training; Step 5: Each client transmits the encrypted optimal parameters to the central server; Step 6: The central server receives the encrypted optimal model parameters uploaded by the client, decrypts them, and applies the adaptive model aggregation strategy to dynamically weighted aggregate the decrypted model parameter data to obtain a global fully connected neural network. The central server scores the quality of the model parameters uploaded by the client, thereby performing weighted aggregation of each client's model parameters based on data quality; The method for performing weighted aggregation based on data quality on the model parameters of each client is: The quality score is calculated based on the model parameters of each client. The specific formula is as follows: Q′(x i )=ω′ com ·C(x i )+ω′ corr ·R(x i )+ω′ cons ·I(x i ) Among them, Q′(x i ) is the quality score of each client model parameter, C(x i ) is the integrity score of the data, R(x i ) is the accuracy score of the data, I(x i ) is the consistency score of the data, ω′ com is the weight of data integrity score, ω′ corr is the weight of the data correctness score, ω′ cons the weights used to score data consistency; According to the quality score Q′(x i ), and set the threshold, when the quality score Q′(x i ) is less than the threshold, it is judged as low-quality data, and different weights are assigned to the uploaded model parameters. The model parameter aggregation formula is: Where N is the number of clients, ω logal is the aggregate weight of the global fully connected neural network, ω i Model parameters uploaded by the client Step 7: Apply the aggregated global fully connected neural network to predict the industrial data, and transmit the model parameters of the global fully connected neural network to each client; Step 8: The client uses the downloaded model parameters to adjust the training frequency and dynamically update the local fully connected neural network; The method for adjusting the training frequency is: Based on the local data quality score of each client, the frequency of its participation in model training is dynamically adjusted. Clients with higher quality participate in more training. The specific formula is as follows: f i =f base ·(1+α·Q′(x i )) Among them, f i is the training frequency of client i, f base is the basic training frequency, α is the adjustment coefficient; The dynamic update method is: The client's training strategy is dynamically adjusted based on the accuracy difference between the local fully connected neural network and the global fully connected neural network, thereby controlling the client's weight in the global model. The specific formula is as follows: Where Δw i (t) is the model parameter update amount of the client at time t, λ is the learning rate adjustment factor, and accuracy i (t)-accuracy global (t) is the accuracy gap between the local model of client i and the global model.

2. The privacy protection method for industrial data transmission according to claim 1, characterized in that: In step 1, the localization processing method includes window size adjustment, noise removal and data cleaning.

3. The privacy protection method for industrial data transmission according to claim 2, characterized in that: The window size adjustment method is: The size of the data aggregation window is dynamically adjusted through the adaptive time series window strategy. The window size is determined based on the volatility and autocorrelation of the data. The expression is as follows: ω(t)=α·σ t +b·r t Among them, α and β are adjustment factors, ω(t) is the dynamically changing window size, σ t is the standard deviation used to measure volatility, ρ t is the autocorrelation coefficient used to measure autocorrelation.

4. The privacy protection method for industrial data transmission according to claim 2, characterized in that: The noise removal method is: Use wavelet transform to extract the high-frequency noise component X of the data high , and remove these noises, retaining only the low-frequency valid data X low , the specific formula is: X denoised =WT -1 (WT(X)·1 |WT(X)|＞θ ) Among them, X denoised is the denoised data, WT(X) is the wavelet transform, θ is the retained noise threshold, 1 |WT(X)|＞θ is the threshold function; By using local statistics, we can calculate the local mean and local variance of the data points to further determine the abnormal noise in the data. The specific formula is: Among them, μ local (x i ) is the local mean, σ local (x i ) is the local variance, and k is the neighbor window size.

5. The privacy protection method for industrial data transmission according to claim 2, characterized in that: The data cleaning method is: By calculating the quality score Q(x i ), and set the threshold, when the quality score Q(x i ) is less than the threshold, it is judged as low-quality data, marked and eliminated. The formula is as follows: Q(x i )=ω com ·C(x i )+ω corr ·R(x i )+ω cons ·I(x i ) Among them, C(x i ) is the integrity score of the data, R(x i ) is the accuracy score of the data, I(x i ) is the consistency score of the data, ω com is the weight of data integrity score, ω corr is the weight of the data correctness score, ω cons The weight with which to score the data consistency.

6. The privacy protection method for industrial data transmission according to claim 1, characterized in that: The local fully connected neural network adopts a privacy protection model of a multilayer perceptron and trains the local fully connected neural network through local data to obtain optimal model parameters.

7. The privacy protection method for industrial data transmission according to claim 5, characterized in that: In step 6, the central server performs quality scoring on the model parameters uploaded by the client, thereby performing weighted aggregation on the model parameters of each client based on data quality.

Images