A method for dynamically configuring and managing underwater acoustic components under an underwater acoustic open architecture
By establishing a component repository, dynamic access control, and machine learning-driven rollback mechanism in the underwater acoustic system, the problems of chaotic component management and insufficient security under the open architecture are solved, and efficient and secure component management and rapid fault recovery are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA SHIP DEV & DESIGN CENT
- Filing Date
- 2026-03-03
- Publication Date
- 2026-06-23
Smart Images
Figure CN121764518B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of underwater acoustic system technology, specifically relating to a dynamic configuration management method for underwater acoustic components under an open underwater acoustic architecture. Background Technology
[0002] Underwater acoustic systems (such as underwater communication, detection, and monitoring systems) play a crucial role in marine engineering, military applications, and scientific research. With technological advancements, underwater acoustic systems are increasingly adopting open architectures to support the flexible integration and dynamic configuration of modular components.
[0003] With the increasing complexity of underwater acoustic detection and communication systems, open architecture and modular design have become the mainstream trend. However, in this dynamic and reconfigurable underwater acoustic environment, traditional component management methods face severe challenges. First, the complexity of component versions and dependencies, coupled with the lack of unified full lifecycle tracking and management, leads to difficulties in component retrieval, low deployment efficiency, and a tendency for version confusion. Second, the diverse sources of components under an open architecture, coupled with the fact that their operation permission management is mostly statically configured, cannot meet the needs of dynamic task scenarios for granular and real-time security control, resulting in security blind spots. Third, the lack of comprehensive audit logs for component operations during system operation makes it difficult to quickly locate the root cause of problems and conduct compliance reviews when failures or security incidents occur. Furthermore, when a component version is found to have defects, manual intervention is usually required for rollback and recovery, resulting in slow response times and failing to guarantee the continuous and stable operation requirements of the underwater acoustic system.
[0004] Therefore, there is an urgent need in this field for an efficient, safe and reliable method for dynamic configuration management of underwater acoustic components to solve the above problems and improve system maintainability and robustness. Summary of the Invention
[0005] In view of this, the purpose of this invention is to provide a dynamic configuration management method for underwater acoustic components under an open underwater acoustic architecture, which realizes full lifecycle management of underwater acoustic components, dynamic access control, multi-dimensional auditing and rapid fault recovery, thereby improving system security and reliability.
[0006] To achieve the above objectives, the present invention provides the following technical solution:
[0007] This invention provides a method for dynamic configuration management of underwater acoustic components under an open underwater acoustic architecture, comprising the following steps:
[0008] S1. Establish an underwater acoustic component repository for full lifecycle tracking and management of underwater acoustic components; this includes tagged registration of underwater acoustic components and assigning a unique component identifier and version number to each registered underwater acoustic component to support rapid tag-based retrieval; at the same time, it provides interfaces for managing and deleting underwater acoustic components.
[0009] S2. Establish a dynamic access control model. Based on the component identifier and version number, divide the underwater acoustic components into different security levels and operation categories, and configure dynamically adjustable permission rules for each underwater acoustic component instance. When an operation request for the target underwater acoustic component is received, the dynamic access control model is used to verify the permission of the operation request to ensure the compliance and security of the component operation.
[0010] S3. When performing an operation on any underwater acoustic component, record the operation log in real time. The operation log shall include at least the operator's identifier, the identifier and version number of the component being operated on, the operation type, the operation timestamp, and the operation result, so as to build a multi-dimensional audit framework for fault analysis, compliance review and behavior optimization.
[0011] S4. Establish a fault rollback mechanism; when a system anomaly is detected due to a defect in the currently deployed active underwater acoustic component version, an automatic rollback operation is triggered; the rollback operation includes: determining the previous stable version of the active underwater acoustic component version based on the operation log, and obtaining the previous stable version from the underwater acoustic component repository for redeployment to replace the defective current version and quickly restore the system to a stable state.
[0012] Furthermore, in step S4, the determination of the previous stable version is based on a machine learning-based stability prediction model, and the specific steps include:
[0013] A1. Extract historical data from the operation log as a training set. The historical data is the data after the feature vector of each version is normalized and reduced in dimensionality through preprocessing. The feature vector includes: version number encoding, deployment timestamp normalized value, operation type distribution vector, operation result statistics, operation time interval sequence, and environment context data.
[0014] A2. Construct a random forest classifier as a stability prediction model. The stability prediction model takes the feature vector as input and outputs the stability probability for each version. :
[0015]
[0016] In the formula, The number of decision trees in the random forest. For the first Decision trees for version The prediction results Indicates stability; For indicator functions;
[0017] A3. Set probability threshold When version Stability probability At that time, set this version as a stable version;
[0018] A4. From all stable versions, apply a timing optimization algorithm to select priority scores. The highest-rated version is used as the previous stable version; if multiple versions have the same score, the version with the earliest deployment time is selected first.
[0019] Furthermore, in step A4, the time-series optimization algorithm constructs a directed graph based on the version deployment sequence, where nodes represent versions and edges represent the deployment order between versions, and uses dynamic programming to calculate the rollback priority score for each version. :
[0020]
[0021] In the formula, For version Deployment timestamp, This is the deployment timestamp of the currently active version; The time decay constant; To balance the weights.
[0022] Furthermore, the random forest classifier consists of multiple decision trees, each of which is trained by sampling samples from the training set using a bootstrap sampling method, and the nodes are split by minimizing Gini impurity; the training process of the model includes: using version labels from historical data, where stable versions are labeled as positive samples and unstable versions are labeled as negative samples.
[0023] Furthermore, before the rollback operation is executed, a simulation test needs to be performed to verify the compatibility and performance of the selected version in a virtual environment to ensure system stability after the rollback.
[0024] Furthermore, in step S1, the method for tagged registration of the underwater acoustic components specifically includes:
[0025] B1. Define a set of standardized labels for each underwater acoustic component. The standardized labels shall include at least the component type, functional category, compatibility information, performance indicators, and security level.
[0026] B2. During registration, an automated tag allocation engine automatically generates and allocates standardized tags based on the metadata of the underwater acoustic components. The metadata is extracted from the configuration files, code comments, test results, or user input of the underwater acoustic components. At the same time, a tag verification module is provided to verify whether the allocated tags conform to the predefined tags.
[0027] B3. Use inverted index technology to associate tags with component identifiers and optimize index updates through distributed storage; when a component is updated or its version changes, automatically synchronize and update the relevant tags and record the tag change history.
[0028] B4. Integrate tag analysis tools to regularly analyze and mine tag data in order to identify the usage patterns of underwater acoustic components, optimize warehouse layout, and predict future demand.
[0029] The beneficial effects of this invention are as follows:
[0030] 1. Solved the problems of chaotic and inefficient component management: By establishing an underwater acoustic component repository and registering and managing the versions of components with tags, the full lifecycle tracking of underwater acoustic components and rapid tag-based retrieval were achieved, which greatly improved the management efficiency and deployment accuracy of components.
[0031] 2. Overcomes the inflexibility of static permission control: By establishing a dynamic access control model based on component identifiers and versions, it realizes fine-grained and dynamic configuration and real-time verification of component operation permissions, effectively improving the security and compliance of component operations under the open architecture.
[0032] 3. It compensates for the lack of operational auditing and fault analysis capabilities: By recording multi-dimensional operation logs in real time, a comprehensive audit framework is built, providing reliable data support for rapid analysis of system faults, compliance review of security incidents, and optimization of user behavior.
[0033] 4. Enables rapid and automatic recovery from system failures: By establishing a failure rollback mechanism based on operation logs, a rollback operation can be automatically triggered when component defects are detected, quickly restoring the system to the previous stable state, which significantly improves the robustness and service continuity of the underwater acoustic system.
[0034] Other advantages, objectives, and features of the invention will be set forth in the following description and will be apparent to those skilled in the art in some respects, or may be learned by practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description
[0035] To make the objectives, technical solutions, and beneficial effects of this invention clearer, the following figures are provided for illustration:
[0036] Figure 1 This is a flowchart of an embodiment of the present invention. Detailed Implementation
[0037] like Figure 1 As shown, this invention provides a method for dynamic configuration management of underwater acoustic components under an open underwater acoustic architecture, comprising the following steps:
[0038] S1. Establish an underwater acoustic component repository for full lifecycle tracking and management of underwater acoustic components; this includes tagged registration of underwater acoustic components and assigning a unique component identifier and version number to each registered underwater acoustic component to support rapid tag-based retrieval; at the same time, it provides interfaces for managing and deleting underwater acoustic components.
[0039] S2. Establish a dynamic access control model. Based on the component identifier and version number, divide the underwater acoustic components into different security levels and operation categories, and configure dynamically adjustable permission rules for each underwater acoustic component instance. When an operation request for the target underwater acoustic component is received, the dynamic access control model is used to verify the permission of the operation request to ensure the compliance and security of the component operation.
[0040] S3. When performing an operation on any underwater acoustic component, record the operation log in real time. The operation log shall include at least the operator's identifier, the identifier and version number of the component being operated on, the operation type, the operation timestamp, and the operation result, so as to build a multi-dimensional audit framework for fault analysis, compliance review and behavior optimization.
[0041] S4. Establish a fault rollback mechanism; when a system anomaly is detected due to a defect in the currently deployed active underwater acoustic component version, an automatic rollback operation is triggered; the rollback operation includes: determining the previous stable version of the active underwater acoustic component version based on the operation log, and obtaining the previous stable version from the underwater acoustic component repository for redeployment to replace the defective current version and quickly restore the system to a stable state.
[0042] In one embodiment of the present invention, the determination of the previous stable version is based on a machine learning stability prediction model, and the specific steps include:
[0043] A1. Extract historical data from the operation logs as the training set. The historical data includes feature vectors for each version. The feature vectors include: version number encoding, normalized deployment timestamp value, operation type distribution vector, operation result statistics (including number of successes, number of failures, and number of retries), operation time interval sequence, and environmental context data (such as water temperature, pressure, and other underwater acoustic parameters). The feature vectors are normalized and dimensionality reduced through preprocessing to ensure data consistency.
[0044] A2. Construct a random forest classifier as a stability prediction model. The stability prediction model takes feature vectors as input and outputs the stability probability of each version. The random forest classifier consists of multiple decision trees. Each decision tree is trained by sampling samples from the training set using the bootstrap sampling method, and node splitting is performed by minimizing Gini impurity. The training process of the model includes: using version labels from historical data, where stable versions are labeled as positive samples (label 1), and unstable versions are labeled as negative samples (label 0). The definition of a stable version is based on preset conditions, such as no errors after deployment, runtime exceeding a threshold, and positive user feedback.
[0045] Among them, stability probability Calculated using the following formula:
[0046]
[0047] In the formula, The number of decision trees in the random forest. For the first Decision trees for version The prediction results (1 indicates stability, 0 indicates instability); For indicator functions;
[0048] A3. Set probability threshold When version Stability probability At that time, set this version as a stable version;
[0049] A4. From all stable versions, apply a timing optimization algorithm to select the previous stable version. The timing optimization algorithm constructs a directed graph based on the version deployment sequence, where nodes represent versions and edges represent the deployment order between versions. Dynamic programming is then used to calculate the rollback priority score for each version. ;
[0050] In the formula, For version Deployment timestamp, This is the deployment timestamp of the currently active version; This is the time decay constant, which is set to twice the system's average deployment interval by default. To balance the weights;
[0051] Select priority score The highest version is used as the previous stable version; if multiple versions have the same score, the version with the earliest deployment time is selected first; at the same time, the system performs a simulation test before rollback to verify the compatibility and performance of the selected version in a virtual environment to ensure system stability after rollback.
[0052] In this solution, the machine learning model is updated periodically and retrained using the latest operation logs to adapt to changes in the behavior of the underwater acoustic components. The fault rollback mechanism also integrates an alarm system that automatically notifies relevant personnel and records an analysis report for subsequent optimization when a rollback operation is triggered. By introducing machine learning models and time-series optimization algorithms, this solution achieves intelligent prediction and selection of the previous stable version, improving the accuracy and adaptability of rollback decisions. It is particularly suitable for the dynamic management of component versions in complex underwater acoustic environments, and reduces rollback risks through probability calculations and simulation tests.
[0053] In one embodiment of the present invention, a method for tagged registration of underwater acoustic components includes:
[0054] B1. Define a set of standardized labels for each underwater acoustic component. These standardized labels should include at least the component type, functional category, compatibility information, performance metrics, and safety level; where:
[0055] The component type is used to distinguish the hardware or software attributes of the underwater acoustic component, the function category describes the specific role the component plays in the underwater acoustic system, and the compatibility information indicates the interoperability requirements between the component and other components.
[0056] Performance metrics include processing latency, bandwidth requirements, power consumption parameters, and reliability scores;
[0057] Security levels are determined based on the sensitivity of the data processed by the component;
[0058] B2. During registration, an automated tag assignment engine automatically generates and assigns standardized tags based on the component's metadata. The metadata is extracted from the component's configuration file, code comments, test results, or user input. At the same time, a tag verification module is provided to verify whether the assigned tags conform to the predefined tags, ensuring the accuracy and consistency of the tags. In addition, the addition of user-defined tags is supported, but they must be approved by the administrator to prevent tag abuse.
[0059] B3. Tag Index Construction Steps: Use inverted index technology to associate tags with component identifiers, and optimize index updates through distributed storage to achieve millisecond-level fast retrieval response; when components are updated or versions change, automatically synchronize and update relevant tags, and record tag change history (including change time, change reason and operator information) to maintain the timeliness and traceability of tags;
[0060] B4. Integrate tag analysis tools to regularly analyze and mine tag data in order to identify the usage patterns of underwater acoustic components, optimize warehouse layout, and predict future demand.
[0061] This solution ensures that each underwater acoustic component receives a comprehensive and consistent metadata description upon registration by defining standardized tags and an automated allocation engine. The tag verification module checks the legality and consistency of tags using a rule engine to avoid human error. Tag indexing utilizes inverted index technology to map tags to component identifiers, enabling efficient retrieval. When components are updated, an automated synchronization mechanism ensures that tags remain consistent with the component's state, while tag analysis tools extract insights from historical data to support decision optimization. The entire process relies on metadata extraction, rule verification, and distributed index management to improve the automation and accuracy of tag processing. This solution enhances the standardization and automation of underwater acoustic component management, reducing errors and delays caused by manual intervention. Through rapid retrieval and index optimization, it significantly improves component search and deployment efficiency. It enhances component traceability and interoperability, facilitating system integration, maintenance, and upgrades. Simultaneously, the tag analysis function provides data support for system optimization, reducing operating costs and improving reliability.
[0062] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made to it in form and detail without departing from the scope defined by the claims of the present invention.
Claims
1. A method for dynamic configuration management of underwater acoustic components under an open underwater acoustic architecture, characterized in that, Includes the following steps: S1. Establish an underwater acoustic component repository for full lifecycle tracking and management of underwater acoustic components; this includes tagged registration of underwater acoustic components and assigning a unique component identifier and version number to each registered underwater acoustic component to support rapid tag-based retrieval; at the same time, it provides interfaces for managing and deleting underwater acoustic components. S2. Establish a dynamic access control model. Based on the component identifier and version number, divide the underwater acoustic components into different security levels and operation categories, and configure dynamically adjustable permission rules for each underwater acoustic component instance. When an operation request for the target underwater acoustic component is received, the dynamic access control model is used to verify the permission of the operation request to ensure the compliance and security of the component operation. S3. When performing an operation on any underwater acoustic component, record the operation log in real time. The operation log shall include at least the operator's identifier, the identifier and version number of the component being operated on, the operation type, the operation timestamp, and the operation result, so as to build a multi-dimensional audit framework for fault analysis, compliance review and behavior optimization. S4. Establish a fault rollback mechanism; When a system anomaly is detected due to a defect in the currently deployed active underwater acoustic component version, a rollback operation is automatically triggered. The rollback operation includes: determining the previous stable version of the active underwater acoustic component version based on the operation log, obtaining the previous stable version from the underwater acoustic component repository, redeploying it to replace the defective current version, and quickly restoring the system to a stable state. In step S4, the determination of the previous stable version is based on a machine learning stability prediction model, and the specific steps include: A1. Extract historical data from the operation log as a training set. The historical data is the data after the feature vector of each version is normalized and reduced in dimensionality through preprocessing. The feature vector includes: version number encoding, deployment timestamp normalized value, operation type distribution vector, operation result statistics, operation time interval sequence, and environment context data. A2. Construct a random forest classifier as a stability prediction model. The stability prediction model takes the feature vector as input and outputs the stability probability for each version. : In the formula, The number of decision trees in the random forest. For the first Decision trees for version The prediction results Indicates stability; For indicator functions; A3. Set probability threshold When version Stability probability At that time, set this version as a stable version; A4. From all stable versions, apply a timing optimization algorithm to select priority scores. The highest-rated version is used as the previous stable version; if multiple versions have the same score, the version with the earliest deployment time is selected first.
2. The method for dynamic configuration management of underwater acoustic components under an open underwater acoustic architecture according to claim 1, characterized in that: In step A4, the time-series optimization algorithm constructs a directed graph based on the version deployment sequence, where nodes represent versions and edges represent the deployment order between versions, and uses dynamic programming to calculate the rollback priority score for each version. : In the formula, For version Deployment timestamp, This is the deployment timestamp of the currently active version; The time decay constant; To balance the weights.
3. The method for dynamic configuration management of underwater acoustic components under an open underwater acoustic architecture according to claim 2, characterized in that: The random forest classifier consists of multiple decision trees. Each decision tree is trained by sampling samples from the training set using the bootstrap sampling method, and the nodes are split by minimizing the Gini impurity. The training process of the model includes using version labels from historical data, where stable versions are labeled as positive samples and unstable versions are labeled as negative samples.
4. The method for dynamic configuration management of underwater acoustic components under an open underwater acoustic architecture according to claim 2, characterized in that: Before performing a rollback operation, a simulation test needs to be performed to verify the compatibility and performance of the selected version in a virtual environment to ensure system stability after the rollback.
5. The method for dynamic configuration management of underwater acoustic components under an open underwater acoustic architecture according to claim 1, characterized in that: In step S1, the method for tagged registration of the underwater acoustic components specifically includes: B1. Define a set of standardized labels for each underwater acoustic component. The standardized labels shall include at least the component type, functional category, compatibility information, performance indicators, and security level. B2. During registration, an automated tag allocation engine automatically generates and allocates standardized tags based on the metadata of the underwater acoustic components. The metadata is extracted from the configuration files, code comments, test results, or user input of the underwater acoustic components. At the same time, a tag verification module is provided to verify whether the allocated tags conform to the predefined tags. B3. Use inverted index technology to associate tags with component identifiers and optimize index updates through distributed storage; when a component is updated or its version changes, automatically synchronize and update the relevant tags and record the tag change history. B4. Integrate tag analysis tools to regularly analyze and mine tag data in order to identify the usage patterns of underwater acoustic components, optimize warehouse layout, and predict future demand.