Modular digital technology deployment system and method based on dynamic adaptation
By constructing a dynamically adaptable modular digital technology deployment system, the problems of poor flexibility, resource waste, and low data security in the Industrial Internet have been solved, realizing real-time and global optimization of the digital transformation of the manufacturing industry, and improving the system's flexibility and data security.
Patent Information
- Application Number
- CN202511355271.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-22
- Publication Date
- 2026-01-09
AI Technical Summary
Existing technologies suffer from poor flexibility, resource waste, insufficient real-time performance, data silos, and low security in the industrial internet and digital transformation. In particular, traditional monolithic architectures, static modular architectures, and cloud-based centralized processing models are unable to meet the dynamic needs and real-time decision-making requirements of manufacturing enterprises.
The system is deployed using modular digital technology based on dynamic adaptation, including a data acquisition layer, an edge computing layer, a dynamic adaptation module library, and a cloud platform layer. Through a hierarchical architecture and bidirectional communication design, it realizes intelligent processing of production data across the entire chain and dynamic scheduling of technical components. Combined with lightweight algorithms, standardized interfaces, and data security mechanisms, it supports on-demand calling and rapid replacement of modules.
It achieves a balance between real-time performance and global optimization in the digital transformation of the manufacturing industry, reduces system deployment costs, improves system flexibility and compatibility, ensures data security, and meets the diverse and dynamic needs of manufacturing enterprises.
Smart Images

Figure CN121309616A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of industrial internet and digital transformation, in particular to a modular digital technology deployment system and method based on dynamic adaptation. BACKGROUND
[0002] In the field of industrial internet and digital transformation, manufacturing enterprises often rely on various digital technology deployment schemes to achieve intelligent upgrading. The existing technologies mainly include traditional monolithic architecture, static modular architecture and cloud centralized processing mode. The traditional monolithic architecture such as Siemens industrial cloud solution adopts a centralized deployment mode, which requires pre-planning of all functional modules. Although it can provide relatively complete services, it has poor flexibility and cannot be dynamically adjusted according to changes in enterprise demand. In addition, the initial investment scale is large, and it requires enterprises to invest a large amount of hardware procurement, system integration and other resources at one time, which puts heavy financial pressure on small and medium-sized enterprises with generally low profit margins. The static modular architecture such as IBM's blockchain platform divides functions into modules, but the module functions are fixed and can only provide preset combination modes. It cannot dynamically adjust the module configuration according to real-time demand such as enterprise production targets and resource constraints, resulting in problems such as resource waste or insufficient functions when enterprise demand changes. The cloud centralized processing mode such as AWS IoT Core relies too much on cloud computing resources, and the edge only undertakes simple data forwarding functions, lacking local real-time decision-making capabilities, resulting in high response delay from data collection to processing, with an average delay often exceeding 200ms, making it difficult to meet real-time decision-making needs such as equipment fault detection and real-time parameter adjustment in the production process.
[0003] In addition, the existing technologies generally do not establish cross-platform standardized interfaces, and different technology ecosystems such as IoT devices, ERP systems and MES platforms have non-uniform interfaces (such as compatibility problems between OPCUA and RESTful API), resulting in high system integration complexity, high cost and serious data island phenomenon. At the same time, there is a lack of targeted protection mechanism in terms of data security, with high risk of industrial data leakage, and it is difficult to adapt to the current situation of shortage of compound talents in the industry due to design flaws in the architecture, which together restricts the depth and breadth of digital transformation of manufacturing industry, and urgently needs a better technical solution to solve it. SUMMARY
[0004] In view of the deficiencies of the prior art, the present application provides a modular digital technology deployment system and method based on dynamic adaptation, which solves the problems raised in the background art.
[0005] In order to achieve the above object, the present application is realized by the following technical scheme: A modular digital technology deployment system based on dynamic adaptation, comprising a data acquisition layer, an edge computing layer, a dynamic adaptation module library and a cloud platform layer, the data acquisition layer is in communication connection with the edge computing layer, the edge computing layer is in bidirectional communication with the dynamic adaptation module library, and the dynamic adaptation module library is in bidirectional communication with the cloud platform layer;
[0006] The data acquisition layer is used for real-time acquisition and preprocessing of production data.
[0007] The edge computing layer is used for deploying lightweight algorithms to execute local real-time decision-making.
[0008] The dynamic adaptation module library is used for storing technology component modules that can be independently called, and generating a module combination scheme based on a dynamic adaptation algorithm.
[0009] The cloud platform layer is used for integrating edge node data for global decision optimization, and realizing data security storage and privacy protection.
[0010] Through the above technical scheme, through the hierarchical architecture and bidirectional communication design of the data acquisition layer, the edge computing layer, the dynamic adaptation module library and the cloud platform layer, the intelligent processing of the whole link of production data and the dynamic scheduling of technology components are realized: the data acquisition layer is used for real-time acquisition and preprocessing of production data to lay the foundation for analysis, the edge computing layer is used for deploying lightweight algorithms to realize local real-time decision-making to ensure response timeliness, the dynamic adaptation module library is used for storing independent technology components and generating an optimal module combination scheme based on an adaptation algorithm to improve system flexibility, and the cloud platform layer is used for integrating data for global decision optimization and realizing data credible management relying on security technology, so as to finally realize the balance of real-time and global optimization, on-demand adaptation of technology components and the collaborative goal of data security guarantee in the digital transformation of manufacturing industry.
[0011] Preferably, the data acquisition layer comprises an Internet of Things sensing unit and a long-distance transmission module, the Internet of Things sensing unit is used for collecting equipment state, environmental parameters and production operation data, and the long-distance transmission module uses low-power wide-area network technology to realize data transmission, thereby reducing wiring cost.
[0012] Through the above technical scheme, the Internet of Things sensing unit is used to collect equipment state, environmental parameters and production operation data to obtain basic information, and the long-distance transmission module uses low-power wide-area network technology to realize data transmission, thereby reducing wiring cost, so as to realize efficient acquisition and low-cost transmission of industrial production data.
[0013] Preferably, the data acquisition layer further integrates a lightweight machine learning model, which is used for noise filtering and feature extraction of original data, thereby reducing invalid data uploaded to the edge computing layer.
[0014] By the technical solution, the original data is filtered and features are extracted by integrating a lightweight machine learning model, and invalid data is reduced to upload to the edge computing layer, thereby achieving double optimization of data quality improvement and transmission load reduction.
[0015] Preferably, the edge computing layer includes an edge computing node and a communication protocol optimization unit. The edge computing node deploys a lightweight intelligent algorithm and a hardware acceleration unit for local real-time decision-making. The communication protocol optimization unit adopts a low-latency communication protocol and a standardized interface protocol to realize low-latency communication and seamless connection between the edge node and the cloud platform layer.
[0016] By the technical solution, the edge computing node deploys a lightweight intelligent algorithm and a hardware acceleration unit to realize local real-time decision-making. The communication protocol optimization unit adopts a low-latency communication protocol and a standardized interface protocol to realize low-latency communication and seamless connection between the edge node and the cloud platform layer, thereby achieving the technical goal of local real-time response and efficient edge-cloud collaboration.
[0017] Preferably, the dynamic adaptation module library is constructed based on the modularization segmentation principle and includes AI algorithm modules, blockchain modules, digital twin modules, and other independent technical components. Each technical component module is provided with standardized input and output interfaces to support on-demand calling and quick replacement of modules.
[0018] By the technical solution, the dynamic adaptation module library is constructed based on the modularization segmentation principle and includes multiple independent technical components. Each module is provided with standardized input and output interfaces to support on-demand calling and quick replacement of modules, thereby realizing flexible combination of technical components and improving system expandability.
[0019] Preferably, the dynamic adaptation algorithm is a module priority evaluation model based on fuzzy entropy. The input of the model is user demand parameters, including production targets and resource constraints. The model generates an optimal module combination scheme and execution priority by calculating the adaptation degree of each module. The weight factors of the adaptation degree include response time, resource occupancy rate, and function matching degree.
[0020] By the technical solution, the dynamic adaptation algorithm is a module priority evaluation model based on fuzzy entropy. The input of the model is user demand parameters, including production targets and resource constraints. The model generates an optimal module combination scheme and execution priority by calculating the adaptation degree of each module. The weight factors of the adaptation degree include response time, resource occupancy rate, and function matching degree.
[0021] Preferably, the cloud platform layer comprises a global decision module and a data security module, the global decision module generates global optimization strategies such as production scheduling adjustment and equipment maintenance plan by using machine learning prediction algorithm, supports multi-objective optimization, and the data security module realizes sensitive data privacy protection and key data trusted storage by using encryption verification technology and tamper-proof storage technology.
[0022] Through the above technical solution, the global decision module generates global optimization strategies by using machine learning prediction algorithm and supports multi-objective optimization, and the data security module realizes data protection by using encryption verification technology and tamper-proof storage technology, thereby realizing the collaborative protection of global decision optimization and data security trusted management.
[0023] A modular digital technology deployment method based on dynamic adaptation, comprising the following steps:
[0024] Step 1: demand analysis, the user defines the production demand through the configuration interface, and the system analyzes the production demand and generates target parameters;
[0025] Step 2: module matching, the dynamic adaptation algorithm selects the optimal module combination from the dynamic adaptation module library, and generates an execution plan;
[0026] Step 3: edge-cloud collaborative execution, the edge computing layer executes real-time control instructions, and the cloud platform layer generates optimization strategies based on global data;
[0027] Step 4: feedback iteration, dynamically adjusting the module combination and algorithm parameters according to the execution results.
[0028] Through the above technical solution, by analyzing the production demand to generate target parameters, selecting the optimal module combination to generate an execution plan, edge-cloud collaborative execution of real-time control and global optimization strategies, and feedback iteration of dynamically adjusting the module combination and parameters, the steps of dynamic matching of technology deployment and production demand and efficient optimization execution of the whole process are realized.
[0029] Preferably, in step 1, the production demand comprises a production optimization target, and the target parameters comprise performance thresholds and time windows, and in step 2, the optimal module combination is determined based on the adaptation degree calculated by the fuzzy entropy algorithm, and the corresponding technology component module combination is dynamically matched according to the production demand.
[0030] Through the above technical solution, by clearly defining the production optimization target and target parameters such as performance thresholds and time windows in the production demand, the adaptation degree is calculated based on the fuzzy entropy algorithm in step 2, and the corresponding technology component module combination is dynamically matched according to the production demand, thereby realizing the accurate correspondence between the module combination and the production optimization demand.
[0031] The application provides a modular digital technology deployment system and method based on dynamic adaptation. The following advantages are provided.
[0032] 1. The application realizes on-demand calling and combination of technical components by constructing a dynamic adaptation module library, and effectively solves the problems of resource waste and insufficient real-time performance in traditional architectures by combining edge-cloud collaborative optimization mechanisms. Among them, the dynamic adaptation algorithm dynamically generates an optimal module combination scheme based on a fuzzy entropy evaluation model, the edge layer lightweight algorithm significantly reduces the response delay of local real-time decision, the cloud platform global optimization strategy realizes efficient resource configuration, the overall system deployment cost is reduced and the flexibility is improved, and the digital transformation needs of manufacturing enterprises at different stages are met.
[0033] 2. The application significantly improves system compatibility and industrial data security by defining cross-platform standardized interfaces and data security mechanisms. The standardized interface supports seamless connection of Internet of Things devices, edge nodes and cloud platforms, reduces the integration cost of cross-technology ecology, and avoids data island phenomenon; at the same time, sensitive industrial data is protected by combining encryption verification technology and tamper-proof storage technology, balancing data sharing and security needs, providing double protection for system integration efficiency and data security in the digital transformation of manufacturing industry. BRIEF DESCRIPTION OF DRAWINGS
[0034] Figure 1 is a system data flow and collaborative process diagram of the application;
[0035] Figure 2 is a dynamic adaptation module combination decision flowchart of the application;
[0036] Figure 3 is an edge-cloud collaborative execution and feedback optimization flowchart of the application;
[0037] Figure 4 is a system architecture diagram of the application;
[0038] Figure 5 is a dynamic adaptation algorithm flowchart of the application. DETAILED DESCRIPTION
[0039] The technical solutions in the embodiments of the application will be described below with reference to the drawings in the application specification. Obviously, the described embodiments are only part of the embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the application.
[0040] Please refer to the drawings in the application specification Figure 1 - the drawings in the application specification Figure 5The embodiment of the application provides a modular digital technology deployment system based on dynamic adaptation, which comprises a data acquisition layer, an edge computing layer, a dynamic adaptation module library and a cloud platform layer, the data acquisition layer is in communication connection with the edge computing layer, the edge computing layer is in bidirectional communication with the dynamic adaptation module library, and the dynamic adaptation module library is in bidirectional communication with the cloud platform layer.
[0041] Specifically, the layered architecture design realizes intelligent processing of industrial data and flexible scheduling of technical components throughout the link, and the layers are cooperatively closed through precise communication connection. The data acquisition layer, as the data entrance of the system, is responsible for real-time acquisition of device status, environmental parameters and production data in the industrial production scene, and transmits the preprocessed data to the edge computing layer; the edge computing layer, as the core of local real-time decision, after receiving the input data of the data acquisition layer, performs local tasks such as device fault detection and real-time parameter adjustment relying on lightweight algorithms, and establishes bidirectional interaction with the dynamic adaptation module library, which not only receives module calling instructions to execute modular algorithms, but also feeds back real-time requirements and processing results to drive module adaptation; the dynamic adaptation module library, as the core scheduling hub of technical components, generates the optimal module combination scheme based on the feedback of the edge layer and the global demand of the cloud platform, realizes on-demand calling and combination of AI, blockchain and other technical components, and forms bidirectional flow of data and decision with the cloud platform layer; the cloud platform layer undertakes the functions of global optimization and data security management, integrates edge node data for global decision optimization, generates production scheduling, maintenance plan and other strategies, and feeds back to the module library and the edge layer, and realizes safe storage and privacy protection of data. The cooperative operation of each level not only guarantees the local real-time requirement, but also realizes global resource optimization and dynamic adaptation of technical components, effectively solving the problems of poor flexibility and complex integration of traditional architecture.
[0042] The data acquisition layer is used for real-time acquisition and preprocessing of production data.
[0043] The data acquisition layer comprises an Internet of Things sensing unit and a long-distance transmission module, the Internet of Things sensing unit is used for acquisition of device status, environmental parameters and production operation data, and the long-distance transmission module realizes data transmission by using low-power wide-area network technology, thereby reducing wiring cost.
[0044] The data acquisition layer also integrates a lightweight machine learning model, which is used for noise filtering and feature extraction of original data, thereby reducing invalid data uploaded to the edge computing layer.
[0045] Specifically, the data acquisition layer, as the core entry point for the system to perceive industrial production scenarios, achieves efficient acquisition and transmission of production data through the collaborative design of IoT sensing units and long-distance transmission modules. Simultaneously, it leverages lightweight machine learning models to improve data quality and reduce transmission load. The IoT sensing units directly face the production site, accurately collecting equipment operating status (such as runtime and fault signals), environmental parameters (such as temperature, humidity, and air pressure), and production operation data (such as energy consumption and production capacity indicators), providing fundamental data support for subsequent analysis and decision-making. The long-distance transmission module employs low-power wide-area network technology, ensuring the stability of long-distance data transmission while significantly reducing the hardware costs and construction complexity associated with traditional cabling, making it particularly suitable for scenarios with wide-area manufacturing plants and dispersed equipment.
[0046] The edge computing layer is used to deploy lightweight algorithms to perform local real-time decision-making;
[0047] The edge computing layer includes edge computing nodes and a communication protocol optimization unit. The edge computing nodes deploy lightweight intelligent algorithms and hardware acceleration units for local real-time decision-making. The communication protocol optimization unit adopts low-latency communication protocols and standardized interface protocols to achieve low-latency communication and seamless integration between the edge nodes and the cloud platform layer.
[0048] Specifically, the edge computing layer, as the core layer for localized real-time decision-making in the system, ensures efficient execution of real-time decisions in industrial scenarios and achieves efficient collaboration with the cloud platform layer through the collaborative design of edge computing nodes and communication protocol optimization units. Edge computing nodes, as the hardware carriers for localized processing, deploy lightweight intelligent algorithms to quickly respond to immediate needs such as equipment fault detection and real-time adjustment of production parameters. They also integrate hardware acceleration units to improve algorithm efficiency, ensuring the timeliness and accuracy of local decisions and effectively compensating for the real-time shortcomings of traditional centralized cloud processing. The communication protocol optimization unit reduces data transmission time by adopting low-latency communication protocols and eliminates technical barriers between edge nodes and the cloud platform layer by combining standardized interface protocols. This enables smooth data interaction and seamless functional integration between the two, ensuring efficient uploading of real-time processing results from the edge and supporting the accurate distribution of global optimization strategies from the cloud platform layer, laying a key technological foundation for the edge-cloud collaborative mechanism.
[0049] The dynamic adaptation module library is used to store independently callable technical component modules and generate module combination schemes based on dynamic adaptation algorithms;
[0050] The dynamic adaptation module library is built on the principle of modular segmentation and includes independent technical components such as AI algorithm modules, blockchain modules, and digital twin modules. Each technical component module has standardized input and output interfaces, supporting on-demand calling and quick replacement of modules.
[0051] The dynamic adaptation algorithm is a module priority evaluation model based on fuzzy entropy. The input of the model is user requirement parameters, including production goals and resource constraints. The model generates the optimal module combination scheme and execution priority by calculating the adaptability of each module. The weighting factors of the adaptability include response time, resource utilization rate and functional matching degree.
[0052] Specifically, the dynamic adaptation module library, as the core hub for scheduling and combining system technical components, achieves flexible invocation and precise matching of technical components through modular segmentation design and intelligent adaptation algorithms. Based on the principle of modular segmentation, it decomposes digital technologies such as AI algorithms, blockchain, and digital twins into independently callable technical component modules. Each module is configured with standardized input and output interfaces, ensuring that different modules can be called on demand, quickly replaced, and flexibly combined according to actual needs, effectively solving the problems of fixed module functions and poor adaptability in traditional architectures. At the same time, the module library has a built-in module priority evaluation model based on fuzzy entropy. Taking user production goals, resource constraints, and other demand parameters as input, it dynamically generates the optimal module combination scheme and execution priority by quantitatively calculating the adaptability weight of each module in dimensions such as response time, resource utilization, and functional matching degree. This enables the system to respond to changes in enterprise production needs in real time, achieve efficient collaboration of technical components and precise allocation of resources, and improve the system's adaptability to the diversified and dynamic needs of the manufacturing industry.
[0053] The cloud platform layer integrates edge node data for global decision optimization and ensures secure data storage and privacy protection. It comprises a global decision-making module and a data security module. The global decision-making module uses machine learning prediction algorithms to generate global optimization strategies such as production scheduling adjustments and equipment maintenance plans, supporting multi-objective optimization. The data security module employs encryption verification technology and tamper-proof storage technology to ensure sensitive data privacy protection and trusted storage of critical data.
[0054] Specifically, the cloud platform layer, as the core layer for system-wide decision-making and data security, achieves globally optimized utilization and secure, reliable management of industrial data through the collaborative operation of the global decision-making module and the data security module. The global decision-making module integrates real-time data uploaded from various edge nodes, leverages machine learning prediction algorithms to deeply analyze production patterns, and generates global optimization strategies such as production scheduling adjustments and equipment maintenance plans. It also supports multi-objective balance optimization, such as minimizing energy consumption and maximizing production capacity, providing enterprises with intelligent decision support at the macro level. The data security module employs encryption and verification technologies to protect the privacy of sensitive industrial data, while combining tamper-proof storage technology to ensure the integrity and traceability of key data (such as production records and energy consumption data), protecting the value of data sharing while preventing the risks of leakage and tampering. The synergistic effect of these two modules enables the cloud platform layer to leverage its global data integration advantages for decision optimization while simultaneously strengthening data security defenses, providing reliable global support and security for the edge-cloud collaborative system.
[0055] A modular digital technology deployment method based on dynamic adaptation includes the following steps:
[0056] Step 1: Requirements Analysis. Users define production requirements through the configuration interface. The system parses the production requirements and generates target parameters. In Step 1, production requirements include production optimization goals, and target parameters include performance thresholds and time windows. In Step 2, the optimal module combination is determined based on the adaptability calculated by the fuzzy entropy algorithm. The corresponding technical component module combination is dynamically matched according to the production requirements.
[0057] Step 2: Module matching. The dynamic adaptation algorithm selects the optimal combination of modules from the dynamic adaptation module library and generates an execution plan.
[0058] Step 3: Edge-cloud collaborative execution, the edge computing layer executes real-time control commands, and the cloud platform layer generates optimization strategies based on global data;
[0059] Step 4: Feedback iteration, dynamically adjust module combination and algorithm parameters based on execution results.
[0060] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A modular digital technology deployment system based on dynamic adaptation, characterized in that, It includes a data acquisition layer, an edge computing layer, a dynamic adaptation module library, and a cloud platform layer. The data acquisition layer is communicatively connected to the edge computing layer, the edge computing layer communicates bidirectionally with the dynamic adaptation module library, and the dynamic adaptation module library communicates bidirectionally with the cloud platform layer. The data acquisition layer is used to collect production data in real time and perform preprocessing. The edge computing layer is used to deploy lightweight algorithms to perform local real-time decision-making. The dynamic adaptation module library is used to store independently callable technical component modules and to generate module combination schemes based on the dynamic adaptation algorithm. The cloud platform layer is used to integrate edge node data for global decision optimization and to achieve secure data storage and privacy protection.
2. The modular digital technology deployment system based on dynamic adaptation according to claim 1, characterized in that, The data acquisition layer includes an IoT sensing unit and a long-distance transmission module. The IoT sensing unit is used to collect equipment status, environmental parameters, and production operation data. The long-distance transmission module uses low-power wide area network technology to achieve data transmission and reduce wiring costs.
3. The modular digital technology deployment system based on dynamic adaptation according to claim 1, characterized in that, The data acquisition layer also integrates a lightweight machine learning model for noise filtering and feature extraction of raw data, reducing invalid data uploaded to the edge computing layer.
4. The modular digital technology deployment system based on dynamic adaptation according to claim 1, characterized in that, The edge computing layer includes edge computing nodes and a communication protocol optimization unit. The edge computing nodes are equipped with lightweight intelligent algorithms and hardware acceleration units for local real-time decision-making. The communication protocol optimization unit adopts low-latency communication protocols and standardized interface protocols to achieve low-latency communication and seamless integration between the edge nodes and the cloud platform layer.
5. A modular digital technology deployment system based on dynamic adaptation according to claim 1, characterized in that, The dynamic adaptation module library is built on the principle of modular segmentation and includes independent technical components such as AI algorithm module, blockchain module and digital twin module; each technical component module has standardized input and output interfaces, supporting on-demand calling and quick replacement of modules.
6. A modular digital technology deployment system based on dynamic adaptation according to claim 1, characterized in that, The dynamic adaptation algorithm is a module priority evaluation model based on fuzzy entropy. The input of the model is user requirement parameters, including production goals and resource constraints. The model generates the optimal module combination scheme and execution priority by calculating the adaptability of each module. The weighting factors of the adaptability include response time, resource utilization rate and functional matching degree.
7. A modular digital technology deployment system based on dynamic adaptation according to claim 1, characterized in that, The cloud platform layer includes a global decision-making module and a data security module. The global decision-making module uses machine learning prediction algorithms to generate global optimization strategies such as production scheduling adjustments and equipment maintenance plans, supporting multi-objective optimization. The data security module uses encryption verification technology and tamper-proof storage technology to achieve sensitive data privacy protection and trusted storage of key data.
8. A method for deploying modular digital technology based on dynamic adaptation, comprising a modular digital technology deployment system based on dynamic adaptation according to any one of claims 1-7, characterized in that, Includes the following steps: Step 1: Requirements analysis. Users define production requirements through the configuration interface, and the system parses the production requirements and generates target parameters. Step 2: Module matching. The dynamic adaptation algorithm selects the optimal combination of modules from the dynamic adaptation module library and generates an execution plan. Step 3: Edge-cloud collaborative execution, the edge computing layer executes real-time control commands, and the cloud platform layer generates optimization strategies based on global data; Step 4: Feedback iteration, dynamically adjust module combination and algorithm parameters based on execution results.
9. The modular digital technology deployment method based on dynamic adaptation according to claim 8, characterized in that, In step 1, the production requirements include production optimization objectives, and the objective parameters include performance thresholds and time windows. In step 2, the optimal module combination is determined based on the adaptability calculated by the fuzzy entropy algorithm, and the corresponding technical component module combination is dynamically matched according to the production requirements.
