Product quality management and tracing system and method based on industrial internet

Abstract

The invention provides a product quality management and traceability system and method based on industrial Internet, which solves the problems of information security and product quality monitoring of the traceability system, and comprises a product management platform, a logistics management platform and a product traceability platform, the product management platform comprises an enterprise information unit, a traceability query unit, an administrative management unit, a law and regulation inspection unit, a monitoring and early warning unit and an information display unit; the logistics management platform comprises a qualification declaration unit, a business management unit, a traceability management unit, an administrative management unit, a regulation inspection unit, a monitoring early warning unit and an information display unit. The product tracing platform comprises a traversal query unit, a field query unit and an index query unit. The method has the advantages of high information security, capability of realizing quality prediction during product traceability and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of product quality management, and specifically relates to a product quality management and traceability system and method based on industrial Internet. Background Art

[0002] At present, the industrial Internet has become a key technology for the transformation and upgrading of the manufacturing industry. As an important means to protect consumer rights and enhance corporate reputation, product quality traceability is becoming increasingly important. Although there are many product quality traceability systems on the market, most systems are insufficient in terms of real-time, accuracy and completeness of data. In the current industrial production field, product quality traceability systems usually rely on traditional information management systems. Although these systems have achieved the recording and management of product information to a certain extent, they have obvious limitations. In the current industrial production field, product quality traceability systems usually rely on traditional information management systems. Although these systems have achieved the recording and management of product information to a certain extent, they have obvious limitations. Centralized data storage methods are vulnerable to cyber attacks, and data security is difficult to guarantee. Information update and processing speeds are slow, and cannot meet the needs of rapid response. Lack of intelligent analysis tools, limited ability to predict potential quality problems.

[0003] In order to solve the shortcomings of the existing technology, people have conducted long-term exploration and proposed various solutions. For example, a Chinese patent document discloses a product quality traceability system based on industrial Internet technology [202410078724.1], which includes a data acquisition layer module, a data processing layer module, a product traceability module, and an application presentation layer module.

[0004] The above solution solves the problem of product quality traceability to a certain extent, but the solution still has many shortcomings, such as poor information security and inability to predict potential product quality problems. Summary of the invention

[0005] The purpose of the present invention is to address the above problems and provide a product quality management and traceability system based on the Industrial Internet with a reasonable design and good product quality management and traceability effects.

[0006] The purpose of the present invention is to provide a product quality management and traceability method based on the industrial Internet that has good prediction effect on potential product quality problems in response to the above problems.

[0007] To achieve the above-mentioned objectives, the present invention adopts the following technical solutions: a product quality management and traceability system based on the industrial Internet, including a product management platform, a logistics management platform and a product traceability platform. The product management platform includes an enterprise information unit, a traceability query unit, an administrative management unit, a regulatory inspection unit, a monitoring and early warning unit and an information display unit; the logistics management platform includes a qualification declaration unit, a business management unit, a traceability management unit, an administrative management unit, a regulatory inspection unit, a monitoring and early warning unit and an information display unit; the product traceability platform includes a traversal query unit, a field query unit and an index query unit.

[0008] In the above-mentioned product quality management and traceability system based on the industrial Internet, the product management platform, logistics management platform and product traceability platform are connected to the cloud platform through the industrial Internet.

[0009] A method for product quality management and traceability system based on industrial Internet, comprising the following steps:

[0010] S1: Analysis of traceability requirements in product production;

[0011] S2: Use blockchain to build a multi-channel traceability system;

[0012] S3: Set product traceability permissions;

[0013] S4: Build a product quality prediction model;

[0014] S5: Product quality management and traceability system testing and evaluation.

[0015] In the above-mentioned product quality management and traceability method based on industrial Internet, step S1 includes the following steps:

[0016] S11: Product production is divided into production, processing, transportation, storage and sales;

[0017] S12: Establish a data set of supply indicators, timestamps, media data, staff tables, account information, and equipment status for each link;

[0018] S13: All data is stored in a distributed encrypted manner.

[0019] In the above-mentioned product quality management and traceability method based on industrial Internet, step S12 includes the following steps:

[0020] S121: Determine the data source and data purpose, read the database and write the address;

[0021] S122: Setting a data conflict resolution method, replacing the original data or abandoning the new data when data conflicts occur;

[0022] S123: Analyze the field differences and format differences between the data source table and the target table, and establish a field mapping relationship;

[0023] S124: Analyze the difference between the codes used in the source table and the target table, and establish a code mapping relationship;

[0024] S125: extracting, converting and loading the main table and the dimension table according to the mapping relationship of step S123 and step S124;

[0025] S126: Processing a custom module for a special mapping relationship.

[0026] In the above-mentioned product quality management and traceability method based on industrial Internet, step S2 includes the following steps:

[0027] S21: Build a blockchain network system, including data layer, network layer, consensus layer, contract layer and application layer;

[0028] S22: Perform hash calculation on the data collected by the data layer through the MD5 algorithm, and store the hash value in the blockchain network system;

[0029] S23: storing the traceability plaintext information in a local database;

[0030] S24: Each field of the stored traceability information is assembled to obtain a block.

[0031] In the above-mentioned product quality management and traceability method based on industrial Internet, step S3 includes the following steps:

[0032] S31: The traceability management authority is divided into three levels, where the first-level management can view all regulatory data, the second-level management can view the public data of the enterprise and the authorized data of external enterprises, and the third-level management can view the public data of the product;

[0033] S32: Encrypt the management authority using the DES algorithm;

[0034] S33: The permission requester sends an authorization request, adds an RSA signature, and the blockchain network uploads the request to the chain;

[0035] S34: The blockchain network adds the request content and determines whether to agree to the authorization. If yes, it encrypts all the request content and uploads it to the IPFS private network and adds an RSA signature to the chain. Otherwise, the authorization is rejected.

[0036] S35: Perform data query and decryption.

[0037] In the above-mentioned product quality management and traceability method based on industrial Internet, step S35 includes:

[0038] S351: Determine whether there is a data batch;

[0039] S352: If there is a data batch, use RSA to verify the signature;

[0040] S353: Obtain all text encryption data according to the batch;

[0041] S354: Decrypt the text data using the DES key;

[0042] S355: Obtain all media encrypted data through the IPFS private network;

[0043] S356: Decrypt the media data using the DES key.

[0044] In the above-mentioned product quality management and traceability method based on industrial Internet, step S4 includes the following steps:

[0045] S41: Product quality data collection;

[0046] S42: pre-process product quality and perform dimension reduction on data;

[0047] S43: product data is divided into a training set and a test set and normalized;

[0048] S44: Establish a BiLSTM model, and input the processed data into the BiLSTM model for learning and training;

[0049] S45: Evaluate the MSE, RMSE, MAE and MAPE of the training results to obtain a prediction model that meets the threshold conditions.

[0050] In the above-mentioned product quality management and traceability method based on industrial Internet, step S5 includes the following steps:

[0051] S51: Determine the evaluation index of the model through expert opinion method;

[0052] S52: Use the analytic hierarchy process to determine the relative importance of each evaluation indicator, measure the original observation value of each evaluation indicator and convert it into a standard value;

[0053] S53: Comprehensively evaluate the model. The evaluation formula is as follows:

[0054]

[0055] Among them, QCI(t) is the model quality evaluation index of the tth period; S j (t) is the evaluation data of the Jth evaluation index; Wj is the weight of the jth evaluation index and the sum of all weight coefficients is 1.

[0056] Compared with the existing technology, the advantages of the present invention are: distributed storage and encryption protection through blockchain technology ensure the security and non-tamperability of data, and at the same time analyze and mine the collected data to identify patterns and trends in the production process, providing data support for optimizing production processes and improving efficiency; building a product quality prediction model to analyze historical data, predict potential quality problems and equipment failures, and achieve preventive maintenance of product production; building a multi-channel traceability system, and setting different permissions to ensure the security of the traceability system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a system structure diagram of the present invention;

[0058] Figure 2 It is the original road map of the method of the present invention;

[0059] Figure 3 It is a flowchart of the blockchain construction of a multi-channel traceability system of the present invention;

[0060] Figure 4 It is a schematic diagram of product traceability authority management of the present invention;

[0061] Figure 5 It is a product quality prediction flow chart of the present invention. DETAILED DESCRIPTION

[0062] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0063] like Figure 1-5 As shown, a product quality management and traceability system based on the industrial Internet includes a product management platform, a logistics management platform and a product traceability platform. The product management platform includes an enterprise information unit, a traceability query unit, an administrative management unit, a regulatory inspection unit, a monitoring and early warning unit and an information display unit; wherein the product management platform relies on a sensor network to monitor key parameters on the production line in real time and provide data support for quality control. The logistics management platform includes a qualification declaration unit, a business management unit, a traceability management unit, an administrative management unit, a regulatory inspection unit, a monitoring and early warning unit and an information display unit; the product traceability platform includes a traversal query unit, a field query unit and an index query unit.

[0064] The product management platform, logistics management platform and product traceability platform each have an information display unit to provide users with convenient access and operation interfaces, and support multi-device and multi-platform access. The enterprise information unit is used to view the basic information of relevant enterprises, the traceability query unit conducts traceability queries on industrial storage and in-and-out warehousing at the product production end, the administrative management unit manages the relevant administrative documents of the enterprise, and the mandatory standards of the product are entered through the regulatory inspection unit. The monitoring and early warning unit monitors the production line in real time through the Internet of Things. The qualification declaration unit uploads the basic information of the enterprise, and the business management unit manages the logistics and distribution status of the enterprise.

[0065] The product traceability platform is open to the public, and uses coding and other methods to track products, relying on blockchain to improve the security of traceability management. The product production information is traced through the product traceability code, and when the product is subsequently processed, packaged or transported, the information is traced through the transaction voucher.

[0066] Specifically, the product management platform, logistics management platform and product traceability platform are connected to the cloud platform through the industrial Internet. The industrial Internet realizes the interconnection of equipment, production lines and supply chains, providing a basis for data collection and analysis. The cloud platform provides powerful data storage and processing capabilities for product quality traceability, allowing enterprises to access and manage traceability information from a central location.

[0067] A method for product quality management and traceability system based on industrial Internet, comprising the following steps:

[0068] S1: Analysis of traceability requirements in product production;

[0069] S2: Use blockchain to build a multi-channel traceability system;

[0070] S3: Set product traceability permissions;

[0071] S4: Build a product quality prediction model;

[0072] S5: Product quality management and traceability system testing and evaluation.

[0073] In depth, step S1 includes the following steps:

[0074] S11: Product production is divided into production, processing, transportation, storage and sales;

[0075] S12: Establish a data set of supply indicators, timestamps, media data, staff tables, account information, and equipment status for each link;

[0076] S13: All data is stored in a distributed encrypted manner.

[0077] Furthermore, since the data comes from different systems and uses different codes, pattern matching and data conversion are required to ensure that the data syntax and semantics are consistent. Step S12 includes the following steps:

[0078] S121: Determine the data source and data purpose, read the database and write the address;

[0079] S122: Setting a data conflict resolution method, replacing the original data or abandoning the new data when data conflicts occur;

[0080] S123: Analyze the field differences and format differences between the data source table and the target table, and establish a field mapping relationship;

[0081] S124: Analyze the difference between the codes used in the source table and the target table, and establish a code mapping relationship;

[0082] S125: extracting, converting and loading the main table and the dimension table according to the mapping relationship of step S123 and step S124;

[0083] S126: Processing a custom module for a special mapping relationship.

[0084] Furthermore, step S2 includes the following steps:

[0085] S21: Build a blockchain network system, including data layer, network layer, consensus layer, contract layer and application layer;

[0086] S22: Perform hash calculation on the data collected by the data layer through the MD5 algorithm, and store the hash value in the blockchain network system, thereby reducing the overall storage pressure of the system;

[0087] S23: storing the traceability plaintext information in a local database;

[0088] S24: Each field of the stored traceability information is assembled to obtain a block.

[0089] In addition, the data collected by industrial production is encrypted by using a symmetric key, which is convenient for the management department to query and monitor. For external query requests, the enterprise needs to grant permission. In order to improve the security of data management, step S3 includes the following steps:

[0090] S31: The traceability management authority is divided into three levels, where the first-level management can view all regulatory data, the second-level management can view the public data of the enterprise and the authorized data of external enterprises, and the third-level management can view the public data of the product;

[0091] S32: The management authority is encrypted using the DES algorithm. This step ensures that the entire process is tracked and recorded by the blockchain. After the entire authorization management is completed, a complete operation record is generated and the record is also unmodifiable;

[0092] S33: The permission requester sends an authorization request, adds an RSA signature, and the blockchain network uploads the request to the chain;

[0093] S34: The blockchain network adds the request content and determines whether to agree to the authorization. If yes, it encrypts all the request content and uploads it to the IPFS private network and adds an RSA signature to the chain. Otherwise, the authorization is rejected.

[0094] S35: Perform data query and decryption.

[0095] Meanwhile, step S35 includes:

[0096] S351: Determine whether there is a data batch, and if so, obtain the batch data by batch number;

[0097] S352: If there is a data batch, use RSA to verify the signature and obtain the data;

[0098] S353: Obtain all text encryption data according to the batch;

[0099] S354: Decrypt the text data using the DES key;

[0100] S355: Obtain all media encrypted data through the IPFS private network;

[0101] S356: The media data is decrypted using the DES key. At this time, the data files of the batch can be browsed. In addition, the identity of the authorization requester and the authorized party is exchanged, and the data query and decryption process is reconstructed through the blockchain network.

[0102] It can be seen that step S4 includes the following steps:

[0103] S41: Product quality data collection;

[0104] S42: Preprocess product quality, reduce the dimension of data, and remove irrelevant feature data, so as to improve the accuracy and efficiency of subsequent model training;

[0105] S43: The product data is divided into a training set and a test set and normalized, the low-dimensional data is nonlinearly transformed, the covariance matrix is ​​constructed, the kernel matrix is ​​introduced and centralized;

[0106] S44: Establish a BiLSTM model, and input the processed data into the BiLSTM model for learning and training;

[0107] S45: Evaluate the MSE, RMSE, MAE and MAPE of the training results to obtain a prediction model that meets the threshold conditions.

[0108] The evaluation indicators of the threshold conditions are as follows:

[0109]

[0110] Obviously, step S5 includes the following steps:

[0111] S51: Determine the evaluation index of the model through expert opinion method;

[0112] S52: Use the analytic hierarchy process to determine the relative importance of each evaluation indicator, measure the original observation value of each evaluation indicator and convert it into a standard value;

[0113] S53: Comprehensively evaluate the model. The evaluation formula is as follows:

[0114]

[0115] Among them, QCI(t) is the model quality evaluation index of the tth period; S j (t) is the evaluation data of the Jth evaluation index; Wj is the weight of the jth evaluation index and the sum of all weight coefficients is 1.

[0116] To sum up, the principle of this embodiment is to build a production quality management and traceability system, use blockchain for multi-channel traceability from the product production link, set corresponding management permissions for the product traceability process, train the product quality prediction model and test the model, and realize product production quality prediction in the process of product traceability investigation.

[0117] The specific embodiments described herein are merely examples of the spirit of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in similar ways, but they will not deviate from the spirit of the present invention or exceed the scope defined by the appended claims.

[0118] Although this article uses more terms such as product management platform, logistics management platform and product traceability platform, it does not exclude the possibility of using other terms. These terms are used only to more conveniently describe and explain the essence of the present invention; interpreting them as any additional restrictions is contrary to the spirit of the present invention.

Claims

1. A product quality management and traceability system based on the industrial Internet, including a product management platform, a logistics management platform and a product traceability platform, characterized in that: The product management platform includes an enterprise information unit, a traceability query unit, an administrative management unit, a regulatory inspection unit, a monitoring and early warning unit, and an information display unit; the logistics management platform includes a qualification declaration unit, a business management unit, a traceability management unit, an administrative management unit, a regulatory inspection unit, a monitoring and early warning unit, and an information display unit; the product traceability platform includes a traversal query unit, a field query unit, and an index query unit.

2. According to the product quality management and traceability system based on industrial Internet in claim 1, it is characterized in that: The product management platform, logistics management platform and product traceability platform are connected to the cloud platform through the industrial Internet.

3. A method for using the product quality management and traceability system based on the industrial Internet according to claim 1, characterized in that: The steps include: S1: Analysis of traceability requirements in product production; S2: Use blockchain to build a multi-channel traceability system; S3: Set product traceability permissions; S4: Build a product quality prediction model; S5: Product quality management and traceability system testing and evaluation.

4. According to claim 3, a method for product quality management and traceability based on the industrial Internet according to claim 1 is characterized in that: The step S1 comprises the following steps: S11: Product production is divided into production, processing, transportation, storage and sales; S12: Establish a data set of supply indicators, timestamps, media data, staff tables, account information, and equipment status for each link; S13: All data is stored in a distributed encrypted manner.

5. According to claim 4, a method for product quality management and traceability based on the industrial Internet according to claim 1 is characterized in that: The step S12 comprises the following steps: S121: Determine the data source and data purpose, read the database and write the address; S122: Setting a data conflict resolution method, replacing the original data or abandoning the new data when data conflicts occur; S123: Analyze the field differences and format differences between the data source table and the target table, and establish a field mapping relationship; S124: Analyze the difference between the codes used in the source table and the target table, and establish a code mapping relationship; S125: extracting, converting and loading the main table and the dimension table according to the mapping relationship of step S123 and step S124; S126: Processing a custom module for a special mapping relationship.

6. The method for product quality management and traceability based on the industrial Internet according to claim 3, wherein: The step S2 comprises the following steps: S21: Build a blockchain network system, including data layer, network layer, consensus layer, contract layer and application layer; S22: Perform hash calculation on the data collected by the data layer through the MD5 algorithm, and store the hash value in the blockchain network system; S23: storing the traceability plaintext information in a local database; S24: Each field of the stored traceability information is assembled to obtain a block.

7. The method for product quality management and traceability based on the industrial Internet according to claim 3, characterized in that: The step S3 comprises the following steps: S31: The traceability management authority is divided into three levels, where the first-level management can view all regulatory data, the second-level management can view the public data of the enterprise and the authorized data of external enterprises, and the third-level management can view the public data of the product; S32: Encrypt the management authority using the DES algorithm; S33: The permission requester sends an authorization request, adds an RSA signature, and the blockchain network uploads the request to the chain; S34: The blockchain network adds the request content and determines whether to agree to the authorization. If yes, it encrypts all the request content and uploads it to the IPFS private network and adds an RSA signature to the chain. Otherwise, the authorization is rejected. S35: Perform data query and decryption.

8. The method for product quality management and traceability based on the industrial Internet according to claim 7, characterized in that: The step S35 comprises: S351: Determine whether there is a data batch; S352: If there is a data batch, use RSA to verify the signature; S353: Obtain all text encryption data according to the batch; S354: Decrypt the text data using the DES key; S355: Obtain all media encrypted data through the IPFS private network; S356: Decrypt the media data using the DES key.

9. The method for product quality management and traceability based on the industrial Internet according to claim 3, characterized in that: The step S4 comprises the following steps: S41: Product quality data collection; S42: pre-process product quality and perform dimension reduction on data; S43: product data is divided into a training set and a test set and normalized; S44: Establish a BiLSTM model, and input the processed data into the BiLSTM model for learning and training; S45: Evaluate the MSE, RMSE, MAE and MAPE of the training results to obtain a prediction model that meets the threshold conditions.

10. The method for product quality management and traceability based on the industrial Internet according to claim 3, characterized in that: The step S5 comprises the following steps: S51: Determine the evaluation index of the model through expert opinion method; S52: Use the analytic hierarchy process to determine the relative importance of each evaluation indicator, measure the original observation value of each evaluation indicator and convert it into a standard value; S53: Comprehensively evaluate the model. The evaluation formula is as follows: Among them, QCI(t) is the model quality evaluation index of the tth period; S j (t) is the evaluation data of the j-th evaluation indicator; Wj is the weight of the j-th evaluation indicator and the sum of all weight coefficients is 1.

Images