Intelligent laboratory equipment internet-of-things unified monitoring operation and maintenance system

Abstract

The invention provides an Internet of Things unified monitoring operation and maintenance system for intelligent laboratory equipment. The system comprises an equipment access module, a data acquisition module, a monitoring analysis module and an operation and maintenance management module. The device access module accesses a plurality of laboratory devices through a unified Internet of Things protocol adaptation layer, and the data acquisition module acquires operation state data of the devices in real time. And the monitoring analysis module intelligently analyzes the data, generates an equipment health state evaluation result and fault early warning information, and helps to judge the health state and potential fault risk of the equipment. And the operation and maintenance management module generates an operation and maintenance task according to the health state evaluation result and the fault early warning information, and coordinates operation and maintenance resources for processing. All the modules carry out data interaction and cooperative control through a unified Internet of Things platform, and high efficiency and accuracy of system operation are ensured. The system can effectively improve the operation and maintenance efficiency of laboratory equipment and reduce the downtime.

Description

A unified IoT monitoring and maintenance system for intelligent laboratory equipment Technical Field

[0001] This application relates to the fields of Internet of Things (IoT) technology, intelligent monitoring and operation and maintenance management, and in particular to a unified IoT monitoring and operation and maintenance system for intelligent laboratory equipment. Background Technology

[0002] With the rapid development of IoT technology, the intelligence and automation levels of laboratory equipment are constantly improving. Especially in high-precision scientific research laboratories, the normal operation of laboratory equipment is crucial to ensuring the accuracy of experimental data and the reliability of experimental results. Therefore, real-time monitoring, status assessment, and fault early warning of laboratory equipment have become important means to ensure the efficient and safe operation of equipment. The introduction of IoT technology makes equipment management more intelligent and convenient. Through the integration of IoT platforms, remote monitoring and management of equipment can be realized, greatly improving the efficiency of laboratory operation and maintenance management.

[0003] Existing laboratory equipment monitoring systems typically employ a single-device monitoring approach, relying on manual, periodic inspections and maintenance. Most of these systems only provide basic operational status monitoring, lacking intelligent analysis and real-time fault prediction capabilities. Their ability to collaboratively manage multiple devices, provide fault early warnings, and adaptively manage operations is weak. Furthermore, existing systems lack in-depth analysis of equipment operational data, failing to quantitatively assess and predict equipment health status, and cannot generate timely maintenance tasks. This results in slow response times and low repair efficiency after faults occur, impacting laboratory work efficiency and the reliability of experimental data.

[0004] While some existing equipment monitoring and management systems can achieve basic equipment monitoring functions, several problems remain. First, most existing systems rely on status data from individual or localized devices, lacking unified management and monitoring of multiple devices. Second, most existing systems only provide simple data acquisition and alarm functions, lacking intelligent analysis and data-driven predictive maintenance. This makes it difficult to detect and address potential problems promptly when equipment malfunctions, often requiring repairs only after failure occurs, failing to provide early warnings and preventative measures. Furthermore, in terms of operation and maintenance management, existing systems typically rely on manual intervention to schedule maintenance tasks, lacking automated task generation and resource coordination mechanisms, resulting in low maintenance efficiency and impacting the overall operational efficiency of the laboratory. Summary of the Invention In view of this, embodiments of the present invention provide a unified monitoring and maintenance system for intelligent laboratory equipment via the Internet of Things to solve at least one of the above-mentioned technical problems.

[0005] According to a first aspect, embodiments of this application provide a unified IoT monitoring and maintenance system for intelligent laboratory equipment, comprising: a device access module for accessing multiple laboratory devices through a unified IoT protocol adaptation layer; a data acquisition module for real-time acquisition of operational status data of the multiple laboratory devices; a monitoring and analysis module for intelligent analysis of the operational status data to generate equipment health status assessment results and fault warning information; and an operation and maintenance management module for generating operation and maintenance tasks based on the equipment health status assessment results and the fault warning information, and coordinating operation and maintenance resources to execute the operation and maintenance tasks.

[0006] In one possible design, the device access module includes: a protocol parsing unit, used to decode the raw heterogeneous protocol data of the access based on a dynamically loaded protocol parsing plugin, and extract standardized device status fields; a data conversion and enhancement unit, used to receive the standardized device status fields, and map and convert them into structured data objects according to a predefined conversion rule template; and an access control unit, used to automatically control the entire lifecycle of laboratory device access, and control the reception, processing and reporting of the structured data objects based on the device access status.

[0007] In one possible design, the data acquisition module includes: a configurable acquisition unit for periodically acquiring operational status data of laboratory equipment according to a predefined acquisition strategy; a real-time processing unit for processing the acquired raw operational status data in real time to obtain processed operational status data; and a data distribution unit for pushing the processed operational status data to the message middleware of the Internet of Things platform in real time for the monitoring and analysis module to subscribe to and consume.

[0008] In one possible design, the monitoring and analysis module includes: a data analysis engine, used to receive the operating status data, perform real-time comparison and statistical analysis of the operating status data based on a preset equipment operating benchmark model, and obtain anomaly and performance deviation identification results; a health assessment unit, used to call a health calculation model matching the laboratory equipment type according to the anomaly and performance deviation identification results, perform quantitative assessment of the laboratory equipment and generate health status assessment results; and an intelligent early warning unit, used to identify and predict progressive failures and / or critical risks in the early stage based on the health status assessment results through a machine learning model, and generate fault early warning information.

[0009] In one possible design, the intelligent early warning unit specifically includes: a progressive failure identification and prediction subunit, used to predict the degradation trend of laboratory equipment performance based on historical sequence data of the health status assessment results through a machine learning model, in order to identify abnormal degradation trajectories, and predict the probability and time of failure within a specific future period based on the identification results; and a critical risk identification and prediction subunit, used to perform real-time pattern recognition and multi-dimensional correlation analysis on preset operating parameter combinations based on the real-time operating status data output by the data analysis engine through a machine learning model, generate risk judgment results characterizing the degree of operational anomalies, and determine whether the laboratory equipment is in or about to enter a critical risk state based on the risk judgment results.

[0010] In one possible design, the input to the progressive failure identification and prediction subunit is the historical sequence of equipment health status assessment results and corresponding timestamps, and the output is a health score prediction sequence within a preset prediction window. In this subunit, a preset degradation threshold is differentially set based on the type of target laboratory equipment, the importance of core components, and historical failure data. The preset degradation threshold is compared with the health score prediction sequence to determine the predicted failure time. Furthermore, the failure probability is obtained through comprehensive quantitative evaluation based on the historical prediction consistency of the time-series degradation prediction model and the fluctuation range of the health score prediction sequence. In the critical risk identification and prediction subunit, the machine learning model is an online anomaly detection model. Its input is the key operating parameter vector and parameter combination features output by the data analysis engine, and its output is a risk score and / or risk category. During real-time inference, the online anomaly detection model determines anomaly patterns that simultaneously meet the condition of exceeding a preset threshold and matching the risk patterns recorded in a preset risk feature library as critical risk states.

[0011] In one possible design, the operation and maintenance management module includes: an operation and maintenance task generation unit, used to calculate an operation and maintenance risk score based on the equipment health and fault impact output by the monitoring and analysis module, and determine the task type, task priority and task time limit requirements of the operation and maintenance task according to the operation and maintenance risk score, and generate a structured operation and maintenance task; and a resource intelligent scheduling unit, used to convert the structured operation and maintenance task into a scheduling constraint set including skill matching, arrival time, spare parts inventory and task time limit constraints, and output scheduling instructions based on a multi-objective optimization algorithm.

[0012] In one possible design, the resource intelligent scheduling unit is used to schedule operation and maintenance resources based on a multi-objective optimization model. The multi-objective optimization model includes at least objective functions that minimize the expected downtime of equipment, minimize the arrival time of operation and maintenance personnel, and minimize the cost of spare parts consumption. Under the condition of satisfying skill matching, spare parts inventory, and task time constraints, it outputs the optimal combination scheduling instructions.

[0013] In one possible design, the operation and maintenance task generation unit includes: a risk score calculation subunit, used to calculate an operation and maintenance risk score based on the equipment health index and fault impact parameters; a task type determination subunit, used to determine the task type of the operation and maintenance task based on the operation and maintenance risk score and fault type; a priority and time limit determination subunit, used to determine the task priority and processing time limit of the operation and maintenance task based on the operation and maintenance risk score and equipment functional importance parameters; and a task structuring generation subunit, used to encapsulate the determined task type, task priority, and processing time limit with the target equipment identifier, handling steps, and acceptance conditions into a structured operation and maintenance task.

[0014] In one possible design, the fault warning information includes a fault impact degree; the fault impact degree is used to quantify the comprehensive impact of potential faults on experimental continuity, equipment safety, and operation and maintenance costs; the intelligent warning unit is used to obtain the fault impact degree based on a comprehensive evaluation of three dimensions, including: a first dimension, which represents the fault type determined by matching abnormal features with a fault mode library; a second dimension, which represents the functional importance level of the target equipment in the experimental process; and a third dimension, which represents the preset attribute information of the current experimental task associated with the target equipment, wherein the preset attribute information includes at least one of the following: task urgency, importance level, progress stage, and the value of associated samples or data.

[0015] In one possible design, the fault warning information includes potential root causes; the intelligent warning unit is used to perform matching analysis between abnormal features based on operating status data and a preset fault mode library to determine the potential root causes; wherein, the fault mode library is stored in a structured manner and integrates equipment manufacturer manuals, historical operation and maintenance data, and industry case data to establish a correspondence between equipment components, abnormal features, and historical fault root causes; the fault mode library supports dynamic updates based on new operation and maintenance data and cases.

[0016] In one possible design, the system may further include a device digital twin module, used to create a digital twin object for each laboratory device, containing structural parameters, operating parameters and alarm events, and to synchronize the operating status data with the digital twin object in real time to form a device health profile.

[0017] In one possible design, the system may further include a security and trust module for performing digital certificate-based identity authentication, least privilege control, and operation auditing for device access, data access, and operation and maintenance, and for encrypting and protecting communication links and stored data.

[0018] According to the second aspect, embodiments of this application provide a unified IoT monitoring and maintenance method for intelligent laboratory equipment, comprising the following steps: connecting multiple laboratory devices through a unified IoT protocol adaptation layer; acquiring operational status data from the connected multiple laboratory devices; analyzing the collected equipment operational status data to generate equipment health status assessment results and fault warning information; automatically generating maintenance tasks based on the health status assessment results and fault warning information; coordinating maintenance resources to execute tasks, and coordinating relevant maintenance resources and executing maintenance operations according to the generated maintenance tasks.

[0019] According to a third aspect, embodiments of this application provide a computing device having the function of implementing the unified monitoring and maintenance method for intelligent laboratory equipment via the Internet of Things as described in the first aspect. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the function.

[0020] According to a fourth aspect, embodiments of this application provide a computer-readable storage medium including instructions. When the instructions are executed on a computer, they cause the computer to perform the unified monitoring and maintenance method for intelligent laboratory equipment via the Internet of Things as described in the first aspect or any possible design of the first aspect.

[0021] According to a fifth aspect, embodiments of this application provide a computing device including a processor, a memory, and a communication interface. The processor is connected to the memory and the communication interface. The memory stores instructions, the processor executes the instructions, and the communication interface communicates with other network elements under the control of the processor. When the processor executes the instructions stored in the memory, it causes the processor to perform the unified monitoring and maintenance method for IoT of intelligent laboratory equipment described in the first aspect or any possible design of the first aspect.

[0022] According to a sixth aspect, embodiments of this application provide a computing device cluster including at least one computing device, wherein the computing device includes a processor and a memory coupled to the processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to cause the computing device to perform the unified monitoring and maintenance method for IoT of intelligent laboratory equipment as described in the first aspect or any possible design of the first aspect.

[0023] According to the seventh aspect, a chip system is provided, wherein the chip system includes a memory and a processor, the memory being used to store a computer program, and the processor being used to call the computer program from the memory and run the computer program, so that a server where the chip is located executes the unified monitoring and maintenance method for IoT of intelligent laboratory equipment as described in the first aspect or any possible design of the first aspect.

[0024] According to the eighth aspect, a computer program product is provided, wherein when the computer program product is run on a server, the server is caused to execute the intelligent laboratory equipment IoT unified monitoring and maintenance method described in the first aspect or any possible design of the first aspect.

[0025] The above technical solution has the following beneficial technical effects: The intelligent laboratory equipment IoT unified monitoring and maintenance system of the present invention integrates equipment access, data acquisition, monitoring and analysis, and maintenance management modules to realize real-time monitoring, health status assessment, and fault early warning of laboratory equipment. This system can collect equipment operating status data in real time, perform intelligent analysis, and generate health assessment results, thereby identifying potential fault risks in advance, automatically generating maintenance tasks, and efficiently coordinating maintenance resources. This improves the intelligence level of equipment management, maintenance efficiency, and fault response speed, reduces equipment downtime and maintenance costs, and ensures the continuous and stable operation of laboratory equipment. Attached Figure Description

[0026] One or more embodiments are illustrated by way of example with the accompanying drawings, which are not intended to limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings are not limited to scale.

[0027] Figure 1 is a schematic diagram of the logical structure of a unified monitoring and maintenance system for intelligent laboratory equipment via the Internet of Things according to an embodiment of the present invention; Figure 2 is a schematic diagram of the logical structure of a device access module according to an embodiment of the present invention; Figure 3 is a schematic diagram of the logical structure of a data acquisition module according to an embodiment of the present invention; Figure 4 is a schematic diagram of the logical structure of a monitoring and analysis module according to an embodiment of the present invention; Figure 5 is a schematic diagram of the logical structure of an intelligent early warning unit according to an embodiment of the present invention; Figure 6 is a schematic diagram of the logical structure of an maintenance management module according to an embodiment of the present invention; Figure 7 is a flowchart of a unified monitoring and maintenance method for intelligent laboratory equipment via the Internet of Things according to an embodiment of the present invention; Figure 8 is a schematic diagram of the structure of a computer system according to an embodiment of the present invention. Detailed Implementation

[0028] The technical solutions in the embodiments of this application are clearly and completely described below with reference to the accompanying drawings. It is obvious that the described embodiments are merely some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this application.

[0029] In the specification, claims, and drawings of this application, the term "comprising" and any other variations thereof are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that comprises a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to the process, method, system, product, or apparatus.

[0030] This application presents various aspects, embodiments, or features within the context of systems comprising multiple devices, components, modules, etc. It should be understood and appreciated that various systems may include additional devices, components, modules, etc., and / or may exclude all devices, components, modules, etc., discussed in conjunction with the accompanying drawings. Furthermore, combinations of these approaches may also be used.

[0031] Furthermore, in the embodiments of this application, the words "exemplary," "for example," etc., are used to indicate examples or illustrations. Any embodiment or design described as "exemplary" in this application should not be construed as a preferred or advantageous embodiment that is superior to other embodiments or designs. Rather, the word "exemplary" is used to present a concept in a specific manner.

[0032] In this application, "related" and "corresponding" can sometimes be used interchangeably. It should be noted that, without emphasizing the distinction, they have the same meaning.

[0033] The business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Even if the architecture evolves and new business scenarios emerge, the technical solutions provided by the embodiments of this application are still applicable to solving similar technical problems.

[0034] As shown in Figure 1, this embodiment of the invention provides a unified IoT monitoring and maintenance system for intelligent laboratory equipment, comprising: a device access module for accessing multiple laboratory devices through a unified IoT protocol adaptation layer; a data acquisition module for real-time acquisition of operating status data of the multiple laboratory devices; a monitoring and analysis module for intelligent analysis of the operating status data to generate equipment health status assessment results and fault warning information; and an operation and maintenance management module for generating operation and maintenance tasks based on the equipment health status assessment results and the fault warning information, and coordinating operation and maintenance resources to execute the operation and maintenance tasks.

[0035] The device access module, data acquisition module, monitoring and analysis module, and operation and maintenance management module interact and coordinate control through a unified IoT platform. The IoT platform uses a unified communication protocol to interact and coordinate control with these modules. The device access module connects to different types of laboratory equipment through the IoT platform, enabling device access, authentication, and registration. The data acquisition module transmits real-time operational status data from multiple laboratory devices to a data storage unit via the IoT platform and provides a data interface for the monitoring and analysis module. The monitoring and analysis module acquires real-time data from the data acquisition module through the IoT platform, compares and analyzes it against a preset equipment operation benchmark model, and generates equipment health status assessment results and fault warning information. The operation and maintenance management module receives fault warning information and health status assessment results generated by the monitoring and analysis module through the IoT platform, coordinates the generation and execution of operation and maintenance tasks, and transmits task information to relevant operation and maintenance personnel and equipment through the IoT platform.

[0036] This embodiment is applicable to laboratory scenarios such as university research, biomedical testing, and industrial R&D. It is compatible with different types / manufacturers of equipment such as chromatographs, mass spectrometers, and centrifuges, achieving unified monitoring and intelligent operation and maintenance throughout the entire lifecycle. Detailed descriptions of each module are as follows: The device access module breaks down protocol barriers through a unified IoT protocol adaptation layer. It has built-in parsing engines for five mainstream protocols: MQTT, CoAP, ModbusTCP, OPCUA, and HTTPS, and supports users adding private protocols through custom interfaces. The module includes a physical access interface unit (RJ45 Ethernet port, Wi-Fi 802.11b / g / n / ac, Bluetooth 5.0, LoRa, USB 3.0) and a protocol conversion unit. The latter uses a configurable protocol mapping rule base to convert the raw data of various devices into a unified JSON format, ensuring that subsequent modules can process the data without distinguishing between device types, adapting to the needs of newly added devices.

[0037] The data acquisition module is used to achieve dynamically adjustable acquisition frequency and ensure data integrity. It includes acquisition task scheduling, data transmission, and data caching units. The scheduling unit presets a basic acquisition frequency according to the importance of the equipment (1 second / acquisition for critical equipment, 10 seconds / acquisition for auxiliary equipment), and automatically increases it to 0.5 seconds / acquisition in case of equipment failure. The transmission unit transmits data using TLS 1.3 encryption. The Redis caching unit can temporarily store 24 hours of data to avoid data loss due to network interruption or module overload. Acquired data includes operating voltage, temperature, core component rotation speed, operating time, task parameters, etc., obtained through the equipment's built-in sensors or controller interfaces.

[0038] The monitoring and analysis module employs an intelligent analysis model integrating machine learning and a multi-dimensional health assessment system, comprising data preprocessing, health status assessment, and fault early warning units. The preprocessing unit cleans, normalizes, and extracts features from the raw data. The assessment unit constructs a model based on four dimensions: performance, core component wear, operational stability, and compliance (weighted at 0.4, 0.3, 0.2, and 0.1 respectively), calculating a 100-point health score and categorizing it into four levels: Excellent (90-100 points), Good (70-89 points), Average (50-69 points), and Poor (less than 50 points), simultaneously outputting the reasons for deductions. The fault early warning unit, based on a trained random forest model, predicts fault types through data feature matching and generates early warning information including risk level, prediction time, and potential consequences according to the probability of occurrence (High ≥80%, Medium 50%-79%, Low 30%-49%). For example, if the temperature of an incubator experiences continuous abnormal fluctuations, the system determines a health score of 65 (Average) and issues a high-risk fault warning for the refrigeration system.

[0039] The operations and maintenance management module is used to intelligently generate operations and maintenance tasks and dynamically schedule resources. It includes task generation, resource scheduling, task tracking, and an operations and maintenance knowledge base. The task generation unit automatically generates three types of tasks based on health levels and warning information: daily maintenance (excellent / good health), fault repair (moderate / poor health with no high-risk warning), and emergency handling (high-risk warning), clearly defining priorities, completion deadlines, required tools, and spare parts. The resource scheduling unit uses a greedy algorithm to match operations and maintenance personnel (based on professional skills and work status) with spare parts inventory, automatically generating a purchase request when insufficient. The task tracking unit monitors progress in real time and feeds back to the monitoring and analysis module to update the health status. The knowledge base unit provides historical case query and solution accumulation functions to assist in efficiently completing operations and maintenance.

[0040] As shown in Figure 2, in some embodiments, the device access module may include: a protocol parsing unit, used to decode the original heterogeneous protocol data accessed through the physical interface based on a dynamically loaded protocol parsing plugin, and extract standardized device status fields; a data conversion and enhancement unit, used to receive the standardized device status fields, and map and convert them into structured data objects that conform to the unified data model within the system according to a predefined conversion rule template; and an access control unit, used to automatically control the entire lifecycle of laboratory device access, and control the reception, processing and reporting of the structured data objects based on the device access status, wherein the entire lifecycle includes at least device discovery, identity authentication, access registration, operation status monitoring and abnormal disconnection handling.

[0041] The device access module is configured as a dynamically pluggable protocol adaptation architecture; the protocol parsing plugin is matched and loaded according to the manufacturer, model and communication protocol version of the target laboratory equipment; the execution of automated management includes active scanning and passive listening for laboratory equipment discovery, laboratory equipment identity authentication based on digital certificates, automatic configuration of access parameters, health monitoring of connection status, and automatic resource reclamation and alarm process when laboratory equipment is abnormally offline.

[0042] The data conversion and enhancement unit is also used to simultaneously attach timestamps, data quality identifiers, and acquisition location tags to the structured data object based on laboratory equipment context information.

[0043] In this embodiment, the device access module adopts a dynamically pluggable protocol adaptation architecture, adapting to different manufacturers and models of chromatographs, centrifuges, incubators, and other equipment in university research, biomedical, and other laboratory scenarios. The specific implementation of each unit is as follows: The protocol parsing unit overcomes manufacturer protocol barriers by dynamically loading protocol parsing plugins. Plugins are stored as independent files (.so for Linux, .dll for Windows), accurately matching the combination of "manufacturer, device model, and communication protocol version." When a device connects via physical interfaces such as RJ45, Wi-Fi, or Bluetooth, the unit automatically reads the device identifier and protocol information. After successful matching, the corresponding plugin is hot-plugged in without requiring a system restart. The plugin decodes the raw data according to its own logic (e.g., Modbus TCP parsing register data, OPCUA extracting node attributes), ultimately outputting standardized status fields such as operating temperature and motor speed, achieving heterogeneous data unification. The data conversion and enhancement unit undertakes the mapping and conversion of standardized fields to the system's unified data model. It has a built-in configurable XML format conversion rule template, supporting custom parameter mapping and unit unification according to device type (e.g., Fahrenheit to Celsius). Upon receiving fields, the system automatically performs data type conversion and formatting, generating a structured data object containing "Device ID, Field Name, Value, Unit, and Collection Time." Simultaneously, it adds three tags based on device context information: a UTC timestamp accurate to milliseconds, a data quality identifier reflecting data integrity and reasonableness (Q0 / Q1 / Q2), and a collection location tag associated with the installation location, improving data traceability and availability. The access control unit is used to achieve automated management and control of the entire device access lifecycle. Device discovery employs both active scanning and passive monitoring modes; identity authentication is based on X.509 digital certificates, allowing access only after verifying the legality of the device certificate; during the registration phase, device numbers are automatically assigned, access parameters are configured, and entries are recorded; connection status is monitored through periodic heartbeat packets, and connection health is determined based on the loss rate; when a device abnormally goes offline, it automatically reclaims occupied resources such as ports and caches, and simultaneously sends an alarm containing device ID and offline time information to the operation and maintenance module, ensuring access security and resource controllability.

[0044] As shown in Figure 3, in some embodiments, the data acquisition module includes: a configurable acquisition unit for periodically acquiring operational status data of laboratory equipment according to a predefined acquisition strategy; a real-time processing unit for real-time cleaning, noise reduction, caching, and format normalization of the acquired raw operational status data to obtain processed operational status data; and a data distribution unit for real-time pushing the processed operational status data to the message middleware of the IoT platform for the monitoring and analysis module to subscribe to and consume.

[0045] The predefined acquisition strategy is an adaptive hierarchical acquisition strategy, which includes: presetting a basic acquisition cycle for different device types and / or different operating parameters; when the device health status assessment result output by the monitoring and analysis module is lower than a preset health threshold and / or the fault warning information reaches a preset warning level, adjusting the acquisition cycle of the target device from the basic acquisition cycle to a high-frequency acquisition cycle not greater than a preset proportion of the basic acquisition cycle; when the device health status recovers to above the health threshold and no abnormal events occur for multiple consecutive acquisition cycles, restoring the acquisition cycle to the basic acquisition cycle or a low-frequency acquisition cycle greater than the basic acquisition cycle; wherein, the adaptive hierarchical acquisition strategy further includes triggering acquisition based on changes in the threshold of adjacent sample value changes, so as to reduce duplicate data uploads.

[0046] As shown in Figure 4, in some embodiments, the monitoring and analysis module includes: a data analysis engine, used to receive and store operating status data from the data acquisition module, and perform real-time comparison and statistical analysis of the operating status data based on a preset equipment operating benchmark model to obtain the identification results of anomalies and performance deviations in the operating status data; a health assessment unit, connected to the data analysis engine, used to call a health calculation model matching the type of laboratory equipment according to the anomaly and performance deviation identification results output by the data analysis engine, to perform quantitative assessment of the laboratory equipment and generate a health status assessment result; and an intelligent early warning unit, connected to the health assessment unit, used to identify and predict progressive failures and / or critical risks in the early stage based on the health status assessment results through an integrated machine learning model, and generate structured fault early warning information.

[0047] This monitoring and analysis module uses a data analysis engine to identify real-time anomalies and performance deviations in operational status data based on a preset equipment operation benchmark model. Combined with the health assessment unit, it calls a health calculation model that matches the equipment type to complete a quantitative assessment. Then, the machine learning model of the intelligent early warning unit enables early prediction of progressive failures and critical risks. This not only significantly improves the accuracy of equipment anomaly identification and the lead time for risk warnings, but also adapts to the differentiated health assessment needs of different types of laboratory equipment, effectively reducing the probability of unplanned equipment downtime and improving the initiative, targeting, and overall efficiency of laboratory equipment operation and maintenance.

[0048] The data analysis engine includes: a benchmark model management unit, used to construct a corresponding equipment operation benchmark model based on equipment type, operating conditions, and historical operating data, and to adaptively update the equipment operation benchmark model when the equipment operating conditions change; a feature extraction and normalization unit, used to extract target operating features from the operating status data and normalize the target operating features to eliminate dimensional differences between different equipment and different operating conditions; and an anomaly and deviation determination unit, used to compare the normalized target operating features with the equipment operation benchmark model in real time, and determine operating anomalies or performance deviations based on the degree of deviation and its duration.

[0049] The health assessment unit includes: an indicator mapping and weight configuration unit, used to map the anomaly and performance deviation identification results output by the data analysis engine to a preset health assessment indicator set according to the laboratory equipment type, and configure indicator weights corresponding to the equipment type for the health assessment indicator set; a health degree fusion calculation unit, used to normalize the health assessment indicator set and perform weighted fusion calculation according to the indicator weights to generate an equipment health degree index, and determine the health level based on the equipment health degree index; and a threshold self-calibration unit, used to adaptively calibrate the threshold parameters of the health assessment indicator set based on the equipment's historical operating data and historical maintenance results, so as to reduce misjudgments and improve the consistency of health assessment.

[0050] The health status assessment results include an equipment health index used to characterize the health level of the equipment; the fault warning information includes at least the warning level, fault probability, fault impact, possible root causes, and handling suggestions.

[0051] The warning level is determined by the intelligent warning unit based on the device health index and a preset threshold range. The warning level includes at least normal, attention, warning and severe levels, with different warning levels corresponding to different health index ranges and response requirements.

[0052] The failure probability is calculated by the intelligent early warning unit based on the historical change sequence of the device health index through a machine learning model. The failure probability is used to characterize the possibility of a functional failure of the device within a preset time window.

[0053] The fault impact is determined by the intelligent early warning unit based on a three-dimensional comprehensive evaluation: first, the fault type (e.g., core component failure, auxiliary function failure, etc.) determined by matching abnormal features with a fault mode library; second, the functional importance of the target equipment in the experimental process (e.g., the hierarchical classification of key detection equipment, core reaction equipment, and auxiliary supporting equipment); and third, key attribute information of the experimental task (including task urgency, importance level, progress stage, and value of associated samples / data). This fault impact is used to quantify the comprehensive impact of the fault on experimental continuity (e.g., whether it leads to task interruption or process stagnation), equipment safety (e.g., whether it causes equipment damage or safety hazards), and operation and maintenance costs (e.g., repair man-hours, spare parts wear and tear, and task rework costs). The formula for calculating the fault impact can be: C fault =w1 F T +w2 F I +w3 F A Among them, C fault Indicates the impact of the failure; w1, w2, w3 are the weighting coefficients of each dimension, F T It is a rating for the type of fault, F I It is a score of the importance of equipment functions, F A This is a score based on task attributes. Core components refer to the critical units within the target laboratory equipment that play a decisive role in its main functional implementation, operational safety, or the validity of experimental results. Their failure will directly lead to equipment malfunction, significant performance degradation, or the inability to continue the experiment. The progress stage refers to the actual stage of the current experimental task associated with the target equipment after proceeding according to the preset execution plan, determined by comparing the preset execution nodes of the experimental task with the actual completion status. The value of associated samples or data refers to the scientific, applied, and economic value of the samples and data involved in the experimental task, dynamically confirmed in advance by factors such as the difficulty of sample collection, preparation costs, and practical application potential.

[0054] The potential root causes are obtained by the intelligent early warning unit through matching analysis of abnormal features in operational status data with a preset fault mode library. This fault mode library contains the correspondence between equipment components, abnormal features, and historical faults. Specifically, the logic for determining the potential root causes is as follows: The intelligent early warning unit first extracts standardized information from the abnormal features in the operational status data, including associated equipment type, component, abnormal parameters, and quantitative performance. Then, the intelligent early warning unit matches this information with the preset fault mode library. This fault mode library uses a structured storage method, integrating equipment manufacturer manuals, historical operation and maintenance data, and industry cases. It establishes the correspondence between equipment components, abnormal features (including parameter types, abnormal performance, and quantitative thresholds), and historical fault root causes, and supports dynamic updates. During matching, candidate fault records are first filtered according to equipment type and component. Next, a similarity algorithm is used to calculate the feature matching degree, and the confidence level is obtained by combining it with the probability of historical fault occurrence. Finally, the candidate root causes are ranked according to the confidence level, and the top three candidate root causes with the highest confidence level and their matching basis are output.

[0055] The proposed handling is generated by the intelligent early warning unit based on the early warning level, possible root causes, and equipment control capability description information. The proposed handling includes at least one of remote handling and manual on-site operation and maintenance.

[0056] As shown in Figure 5, in some embodiments, the intelligent early warning unit specifically includes: a progressive failure identification and prediction subunit, used to predict the degradation trend of laboratory equipment performance based on historical sequence data of the health status assessment results through a machine learning model, so as to identify abnormal degradation trajectories that deviate from the normal performance degradation mode, and predict the probability and time of functional failure in a specific future period based on the identification results; and a critical risk identification and prediction subunit, used to perform real-time pattern recognition and multi-dimensional correlation analysis on preset operating parameter combinations based on the real-time operating status data output by the data analysis engine through a machine learning model, generate risk judgment results that characterize the degree of operational abnormality or conform to a preset risk feature library, and determine whether the laboratory equipment is in or about to enter a critical risk state that requires immediate intervention based on the risk judgment results.

[0057] The machine learning model of the progressive fault identification and prediction subunit is a temporal degradation prediction model. Its input is the historical sequence of equipment health status assessment results and corresponding timestamps, and its output is the health score prediction sequence and / or remaining life estimate within a preset prediction window. The temporal degradation prediction model is trained using a long short-term memory network or a gated recurrent unit. The training samples are generated by labeling historical health sequences and actual fault occurrence times, and the fault probability and fault time are determined by the intersection time of the health score prediction sequence and the preset degradation threshold.

[0058] Among them, the health score prediction sequence is a sequence of predicted values ​​of the equipment's health status over a future period, generated by a time-series degradation prediction model (such as a long short-term memory network or a gated recurrent unit) based on historical data of the equipment's health status assessment results. It is used to represent the trend of health changes of the equipment within the prediction window and help determine the probability and timing of possible equipment failures.

[0059] The method of determining the failure probability and failure time by the intersection of the health score prediction sequence and the preset degradation threshold is as follows: First, based on the type of laboratory equipment, the importance of core components, and historical failure data, differentiated preset degradation thresholds are set for different equipment or components. These preset degradation thresholds serve as a quantitative standard for judging whether the equipment performance has deteriorated to a critical state. The health score prediction sequence output by the time-series degradation prediction model is a quantitative data of health metrics covering continuous time nodes within the future preset prediction window, forming a continuous performance degradation trajectory in chronological order. When the value in the health score prediction sequence first drops below or equals the preset degradation threshold, this time node is the intersection of the two, and this time is directly determined as the predicted failure time. At the same time, by combining factors such as the degree of consistency between the historical health score sequence and the actual failure time during model training, and the fluctuation range of the prediction sequence, the probability of failure corresponding to this intersection time is quantitatively evaluated, thereby determining the failure probability. This ensures that the determination of failure time and probability is based on objective data and clear logic, and has verifiability and accuracy.

[0060] In practice, the calculation formula for the differentiated preset degradation threshold is as follows: In the formula, T d,i,j A differentially preset degradation threshold (0~100, the critical value for health score, the lower the value, the more severe the performance degradation) is set for the j-th core component of the i-th type of laboratory equipment; T 0,i The baseline degradation threshold for the i-th type of equipment is determined based on the factory standards and industry maintenance specifications for the same type of equipment (e.g., chromatograph T). 0,i =60, Centrifuge T 0,i =55); W j The importance normalization weight for the j-th core component is defined as follows: (0.7~0.9 for core components, 0.4~0.6 for important components, and 0.2~0.3 for auxiliary core components); α is the historical failure frequency correction coefficient (0.1~0.3, empirically calibrated); F i,j The historical failure frequency (number of occurrences within the statistical period) of the j-th component of the i-th type of equipment. The average historical failure frequency of all core components of the i-th type of equipment ( ); β is the fault loss correction factor (0.05~0.15, empirically calibrated); Si,j The average downtime (in hours) after the failure of the j-th component of the i-th type of equipment; max(S i ) represents the maximum downtime after all core components of the i-th type of equipment fail.

[0061] In practical implementation, the formula for calculating the historical prediction consistency C of the time-series degradation prediction model is as follows: The formula for calculating the volatility V of the health score prediction sequence is as follows: The formula for calculating the failure probability P is as follows: In the formula, P represents the probability of equipment failure, ranging from [0,1]. The closer the value is to 1, the higher the probability of equipment failure within the preset prediction window. C represents the historical prediction consistency of the time-series degradation prediction model, ranging from [0,1]. The closer the value is to 1, the higher the consistency between the model's past prediction results and the actual health score. m represents the number of historical prediction samples consistent with the current equipment type and core components (the sample size is recommended to be ≥30 groups). H p,k H represents the model's predicted health score (0-100) for the k-th historical sample. a,k σ(H) represents the actual health score (0-100) of the k-th historical sample; V represents the fluctuation range of the predicted health score sequence, ranging from [0, +∞). The closer the value is to 0, the more stable the predicted health score sequence within the preset prediction window will be. s ) represents the standard deviation of the health score prediction sequence, μ(H) s H represents the mean of the predicted health score series. s A health score prediction sequence (containing prediction values ​​for t consecutive time nodes, where t is set according to laboratory operation and maintenance requirements) is preset within a prediction window for the future; K is the equipment type risk calibration coefficient, with a value range of [0.8, 1.2]. For high-precision laboratory equipment (such as mass spectrometers and chromatographs), the coefficient is 1.0~1.2, and for conventional laboratory equipment (such as incubators and centrifuges), the coefficient is 0.8~1.0. It is obtained by calibration based on historical fault data of the same type of equipment; min and max are extreme value functions used to constrain the fault probability results within a reasonable range of [0,1] to avoid risk misjudgment caused by extreme calculation values.

[0062] The machine learning model of the critical risk identification and prediction subunit is an online anomaly detection model. Its input is the key operating parameter vector and parameter combination features output by the data analysis engine, and its output is the risk score and / or risk category. The online anomaly detection model uses an isolated forest or a support vector machine to build a normal operating condition model, and in real-time inference, it determines the anomaly pattern that exceeds the preset threshold and matches the preset risk feature library as a critical risk state.

[0063] As shown in Figure 6, in some embodiments, the operation and maintenance management module may specifically include: an operation and maintenance task generation unit, used to calculate an operation and maintenance risk score based on the equipment health and fault impact output by the monitoring and analysis module, and adaptively determine the task type, task priority, and task time limit requirements of the operation and maintenance task according to the operation and maintenance risk score, generating a structured operation and maintenance task; a resource intelligent scheduling unit, used to transform the structured operation and maintenance task into a scheduling constraint set including skill matching, arrival time, spare parts inventory, and task time limit constraints, and based on a multi-objective optimization algorithm, under the condition of simultaneously satisfying the scheduling constraints, with the optimization objective of minimizing the expected downtime of the equipment and / or minimizing the consumption of operation and maintenance resources, to perform combined optimization of operation and maintenance personnel, spare parts, and tools to output scheduling instructions; and a task execution tracking and feedback unit, used to collect the operation and maintenance operation sequence, handling time, and the equipment operating status or health assessment results obtained after the operation and maintenance handling is completed during the execution of the operation and maintenance task, and write the above-collected data back to the IoT platform as feedback data to update the equipment health threshold and / or fault mode library.

[0064] In some embodiments, the operation and maintenance task generation unit includes: a risk score calculation subunit, used to calculate an operation and maintenance risk score based on the equipment health index and fault impact parameters; the specific calculation process of the risk score calculation subunit is as follows: the operation and maintenance risk score is quantified using a weighted summation formula, the formula being R=w1×(1-H / 100)+w2×C fault Where R represents the operation and maintenance risk score, ranging from 0 to 1, with higher values ​​indicating higher operation and maintenance risks; w1 and w2 are preset weighting coefficients, the sum of which is 1, which can be flexibly configured according to the laboratory equipment management needs. For example, w1=0.6 and w2=0.4 can be set for core experimental equipment, and w1=0.4 and w2=0.6 can be set for auxiliary equipment; H is the equipment health index, ranging from 0 to 100, output by the health assessment unit; C fault The failure impact score, ranging from 0 to 10, is derived through a comprehensive evaluation of failure type, equipment functional importance, and key attributes of the experimental task. The calculation first normalizes the health index by subtracting the ratio of the health index to 100 from 1, converting it into a quantitative value representing the degree of health degradation. This value is then multiplied by the failure impact score by its corresponding weight, and finally summed to obtain a standardized operational risk score. This ensures that the score objectively reflects the comprehensive risk level of equipment health status and failure impact.

[0065] The task type determination subunit is used to determine the task type of the maintenance task based on the maintenance risk score and fault type. Specifically, the task type determination subunit is used to pre-set three-level thresholds for the maintenance risk score (low risk ≤ 0.3, 0.3 < medium risk ≤ 0.7, high risk > 0.7) based on the maintenance scenario requirements of the laboratory equipment, and to classify the fault type into four categories: core component fault, auxiliary function fault, performance degradation fault, and safety-related fault, and to establish a mapping rule library between "risk score range - fault type" and task type. When the maintenance risk score and fault type are received, the risk range to which the score belongs is first determined, and then the mapping rule is matched with the fault type. When low risk is matched with auxiliary function fault or performance degradation fault, a routine maintenance task is generated. When medium risk is matched with core component fault or performance degradation fault, a planned maintenance task is generated. When high risk is matched with any fault type or low to medium risk is matched with safety-related fault, an emergency response task is generated. The mapping rule library supports dynamic adjustment according to the laboratory equipment type and maintenance strategy to ensure that the task type determination is accurately adapted to the actual maintenance needs.

[0066] The priority and time limit determination subunit is used to determine the task priority and processing time limit of the operation and maintenance tasks based on the operation and maintenance risk score and equipment functional importance parameters. The specific implementation process of the priority and time limit determination subunit is as follows: First, the equipment functional importance parameters are quantified and graded according to their role in the experimental process, with core key equipment assigned a value of 1.0, important functional equipment assigned a value of 0.8, general functional equipment assigned a value of 0.6, and auxiliary supporting equipment assigned a value of 0.4. The priority score is calculated using the formula P=0.6R+0.4F (where P is the priority score and R is the operation and maintenance risk score). The scoring system (ranging from 0 to 1, with F representing the quantified importance of the equipment's function) is used to map the score range to priorities and processing time limits. A pre-defined mapping rule is established: P ≥ 0.8 corresponds to Level 1 priority with a processing time limit of 2 hours; 0.6 ≤ P < 0.8 corresponds to Level 2 priority with a processing time limit of 4 hours; 0.4 ≤ P < 0.6 corresponds to Level 3 priority with a processing time limit of 24 hours; and P < 0.4 corresponds to Level 4 priority with a processing time limit of 72 hours. This mapping rule supports dynamic adjustment based on laboratory maintenance strategies to ensure that priorities and time limits match the actual risks and equipment importance.

[0067] The task structuring generation subunit is used to encapsulate the determined task type, task priority, and processing time limit, along with the target equipment identifier, handling steps, and acceptance conditions, into a structured maintenance task. The task structuring generation subunit works as follows: All key information is integrated according to a preset standardized data format. The target equipment identifier includes the equipment's unique number, installation location, model, and the laboratory zone it belongs to. The handling steps are generated based on historically effective solutions in the fault mode library and equipment manufacturer specifications, clearly defining the operation process, required tools, and spare parts models. Acceptance conditions are quantified as the equipment health index threshold, the normal range of core operating parameters, and the required stable operating time. Finally, the task type, priority, processing time limit, and the above information are encapsulated into unified structured data, which can be directly synchronized to maintenance personnel terminals and the system management platform for rapid execution and full-process tracking.

[0068] In some embodiments, the intelligent resource scheduling unit is used to schedule maintenance resources based on a multi-objective optimization model. The multi-objective optimization model includes at least objective functions for minimizing expected equipment downtime, minimizing maintenance personnel arrival time, and minimizing spare parts consumption costs. Under the conditions of satisfying skill matching, spare parts inventory, and task time constraints, it outputs the optimal combination scheduling instructions corresponding to personnel, spare parts, and tools. In one example, the implementation process of the intelligent resource scheduling unit is as follows: First, it collects core data such as the maintenance personnel skill matrix, real-time location and busy / idle status, spare parts inventory quantity, storage location and unit price, and the equipment location, required skills, and spare parts model corresponding to the task. Then, it constructs a multi-objective optimization model, whose objective function is: Min Z = α × Tdown + β × Tarr + γ × Cspare (where Z is the comprehensive optimization target value, α, β, and γ are weight coefficients and α + β + γ = 1, which can be dynamically configured according to the laboratory operation and maintenance priority; Tdown is the expected downtime of the equipment, which is equal to the sum of the scheduling delay time and the standard task processing time; Tarr is the arrival time of the operation and maintenance personnel, calculated based on the optimal path between the current location of the personnel and the location of the equipment; Cspare is the cost of spare parts consumption, which is equal to the unit price of the spare parts × the quantity consumed × the loss coefficient). At the same time, the following constraints are set: the matching degree between the operation and maintenance personnel skills and the task requirements is ≥ 85%, the available quantity of spare parts inventory is ≥ the quantity required by the task, and the total task processing time (Tarr + standard task processing time) is ≤ the task processing time limit. The model is solved by genetic algorithm, and the optimal combination scheduling instructions of personnel, spare parts, and tools are output. The optimal path for assigning operation and maintenance personnel with matching skills and retrieving corresponding spare parts and tools is clearly defined, so as to ensure that the comprehensive optimization of the three major objectives is achieved under multiple constraints.

[0069] In other embodiments, the intelligent resource scheduling unit is used to schedule operation and maintenance resources based on a multi-objective optimization model. The multi-objective optimization model includes at least the objective functions of minimizing the expected downtime of equipment, minimizing the arrival time of operation and maintenance personnel, minimizing the cost of spare parts consumption, minimizing the value loss of equipment-related experimental tasks, minimizing the risk probability of secondary damage to equipment during operation and maintenance, minimizing the failure loss of related experimental samples / data, and maximizing the probability of fault-free operation of equipment within a preset period after operation and maintenance. The unit outputs the optimal combination scheduling instructions under the conditions of skill matching, spare parts inventory, task time limit, and special laboratory environment operation specifications.

[0070] In some embodiments, when determining the task type of an operation and maintenance task, the task type determination subunit is specifically used to: before generating the operation and maintenance task, determine whether the target device supports remote control operation and meets the remote handling conditions based on the fault type and the device control capability description information recorded by the target device in the IoT platform; when the remote handling conditions are met, prioritize generating a remote self-healing operation and maintenance task, and issue a remote control instruction to the target device, the remote control instruction including a reset control instruction for triggering the device to perform a restart or state recovery operation, a parameter configuration instruction for adjusting the device's operating threshold or operating parameters, and / or a current limiting control instruction for limiting the device's output power or operating load; after the remote self-healing operation and maintenance task is executed, re-collect the operating status data of the target device and perform a health status assessment; when the health status assessment result does not meet the preset recovery conditions, automatically upgrade to generate a manual on-site operation and maintenance task and call the resource intelligent scheduling unit to generate and issue the corresponding scheduling instruction.

[0071] In some embodiments, the specific working process of the task execution tracking and feedback unit is as follows: During the execution of the operation and maintenance task, the standardized operation and maintenance operation sequence (including actual operation steps, key parameter adjustments and tool usage records) and the time consumption of each stage (travel time, maintenance time, debugging time) are collected in real time through the operation and maintenance personnel terminal. After the task is completed, the core operating parameters of the equipment (such as temperature, speed, voltage) are automatically re-collected, and the post-handling health index is calculated through the health assessment model. The above data is written back to the IoT platform as feedback data. The IoT platform updates the equipment health threshold and fault mode library based on the feedback data, wherein the health threshold update adopts the following formula: H_new=ω×H_prev+(1 ω)×λ×H_curr (ω is the historical threshold weight, ranging from 0.6 to 0.8, H_prev is the original health threshold, H_new refers to the health assessment threshold updated by the IoT platform after the device has undergone maintenance and repair, λ is the data reliability coefficient after repair, determined based on the stable operating time of the device, λ=1.0 when the device has been running stably for ≥24 hours, and H_curr is the health index after repair), and at the same time, the associated information of "maintenance operation sequence, repair effect, and device status change" is added to the fault mode library to achieve continuous optimization of the accuracy of health assessment and fault matching.

[0072] In some embodiments, the system may further include a digital twin module for each laboratory device, used to create a digital twin object containing structural parameters, operating parameters, and alarm events, and to synchronize the operating status data with the digital twin object in real time to form a device health profile and support visual tracking. Specifically, for each laboratory device, a digital twin object containing structural parameters (model, component composition, installation dimensions, design rated parameters), operating parameters (temperature, speed, voltage, etc. output by the real-time synchronized data acquisition module), and alarm events (historical and real-time fault warnings, anomaly alerts) is constructed based on the device's factory technical documents, installation configuration parameters, and core component specifications. The system synchronizes the device's real-time operating status data with the digital twin object at millisecond levels via an Internet of Things (IoT) protocol, dynamically integrating the data to form a visual health profile covering the device's health status throughout its entire lifecycle. It also supports visual tracking of the device's operating trajectory, health changes, and alarm correlations in the form of 3D models, status dashboards, and data trend curves, providing intuitive data support for operation and maintenance decisions.

[0073] The equipment digital twin module includes: a twin modeling unit, used to construct a digital twin model corresponding to the laboratory equipment based on equipment type information and equipment configuration data, the digital twin model including equipment structural parameters, operating parameter definitions, and component hierarchical relationships; a status synchronization unit, used to map and update the operating status data and alarm event data from the data acquisition module to the digital twin model in real time to maintain the consistency between the digital twin model and the physical equipment operating status; a health profile generation unit, used to generate a multi-dimensional health profile representing the equipment's operating health level based on the operating parameters, historical status changes, and alarm events in the digital twin model; and a visualization tracking unit, used to visualize the digital twin model and the health profile, and support the time-series tracking and display of equipment operating status, historical trajectory, and alarm events.

[0074] In some embodiments, the system may further include a security and trust module for performing digital certificate-based identity authentication, least privilege control, and operation auditing for device access, data access, and maintenance operations, and for encrypting and protecting communication links and stored data. Specifically, the security and trust module adopts a full-link security architecture. When a device accesses the system, it completes two-way identity verification using a pre-installed X.509 digital certificate. Data access and maintenance operations require secondary authentication via personnel hardware UKey certificates and dynamic passwords. A least privilege control mechanism based on roles and data tags allocates refined permissions according to device type and operation scenario (e.g., only allowing maintenance personnel to access associated device data, only opening necessary operation interfaces), preventing unauthorized access. The communication link uses TLS 1.3 protocol for encrypted transmission, and stored data is encrypted using the AES-256-GCM algorithm and dynamically managed by a key management system (KMS). Simultaneously, it automatically records device access logs, data access trajectories, and the entire maintenance operation process (including operator, time, content, and result), forming an immutable chain audit log that supports traceability by device, personnel, and time dimensions, ensuring system security and trustworthiness and full auditability of operations.

[0075] The security, trust, and auditing module includes: an identity authentication unit, used to verify the identities of accessed laboratory equipment, user terminals, and operation and maintenance nodes based on digital certificates, and assign a unique security identity identifier to them after successful authentication; a permission control unit, used to implement least-privilege control over device access, data access, and operation and maintenance operations based on the security identity identifier and preset permission policies, and dynamically update access control rules when permissions change; a secure communication unit, used to perform encrypted transmission of data communication links between devices and the IoT platform, and perform integrity verification on control commands and sensitive data that affect the device's operating status to prevent data tampering and illegal injection; a secure storage unit, used to encrypt and store device data, operation and maintenance records, and audit logs stored in the IoT platform, and control data decryption access based on key generation, storage, and update policies; and an operation auditing unit, used to record the entire process of device access behavior, data access behavior, and operation and maintenance behavior, and generate audit logs containing the operation subject, operation time, operation content, and results to support security traceability and compliance auditing.

[0076] As shown in Figure 7, an embodiment of this application provides a unified IoT monitoring and maintenance method for intelligent laboratory equipment, which includes the following steps: S710: Connecting multiple laboratory devices through a unified IoT protocol adaptation layer; S720: Obtaining operating status data from the connected laboratory devices; S730: Analyzing the collected device operating status data to generate device health status assessment results and fault warning information; S740: Automatically generating maintenance tasks based on the health status assessment results and fault warning information; S750: Coordinating maintenance resources to execute tasks, coordinating relevant maintenance resources and executing maintenance operations according to the generated maintenance tasks.

[0077] As shown in Figure 8, the computing device 800 may include a transceiver 801, a processor 802, and a memory 803. The memory 803 may be used to store code, instructions, etc., executed by the processor 802.

[0078] It should be understood that the processor 802 can be an integrated circuit chip with signal processing capabilities. In implementation, the various steps of the above method embodiments can be completed by hardware integrated logic circuits in the processor or by software instructions. The processor can be a general-purpose processor, a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), a system-on-chip (SoC), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The processor can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor, or it can be any common processor. The steps of the methods disclosed in the embodiments of this application can be directly executed by a hardware decoding processor, or executed using a combination of hardware and software modules in the decoding processor. The software modules can be located in storage media that are well-established in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with the hardware in the processor, completes the steps of the above methods.

[0079] It is understood that the memory 803 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of RAM can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0080] It should be noted that the memory of the systems and methods described in this specification includes, but is not limited to, these memories and any other suitable types of memory.

[0081] Embodiments of this application also provide a system-on-a-chip (SoC), which includes an input / output interface, at least one processor, at least one memory, and a bus. The at least one memory is used to store instructions, and the at least one processor is used to invoke the instructions from the at least one memory to perform the operations of the methods described above.

[0082] Embodiments of this application also provide a computer storage medium, wherein the computer storage medium can store program instructions to execute any of the methods described above. Optionally, the storage medium may specifically be a memory 703.

[0083] Those skilled in the art will recognize that the units and algorithm steps described in conjunction with the embodiments disclosed in this specification can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0084] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the above-described systems, devices, and units can be referred to the corresponding processes in the above method embodiments. Further details will not be repeated here.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the described apparatus embodiments are merely exemplary. For example, the unit division is only a logical functional division, and other division methods may be used in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not performed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed can be implemented through some interfaces. Indirect coupling or communication connection between devices or units can be implemented electronically, mechanically, or otherwise.

[0086] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0087] In addition, the functional units in the embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0088] When these functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for instructing a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the embodiments of this application. The aforementioned storage medium includes any medium capable of storing program code, such as a USB flash drive, a removable hard disk, read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0089] The above description is merely some specific implementations of this application and is not intended to limit the scope of protection of this application. Any variations or substitutions easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A unified IoT monitoring and maintenance system for intelligent laboratory equipment, characterized in that, include: The device access module is used to connect multiple laboratory devices through a unified IoT protocol adaptation layer; The data acquisition module is used to collect the operating status data of the multiple laboratory devices in real time; The monitoring and analysis module is used to intelligently analyze the operating status data and generate equipment health status assessment results and fault early warning information. The operation and maintenance management module is used to generate operation and maintenance tasks based on the equipment health status assessment results and the fault warning information, and to coordinate operation and maintenance resources to execute the operation and maintenance tasks.

2. The system according to claim 1, characterized in that, The device access module includes: a protocol parsing unit, used to decode the original heterogeneous protocol data of the access based on a dynamically loaded protocol parsing plugin, and extract standardized device status fields; a data conversion and enhancement unit, used to receive the standardized device status fields, and map and convert them into structured data objects according to a predefined conversion rule template; and an access management and control unit, used to automatically manage the entire lifecycle of laboratory device access, and control the reception, processing and reporting of the structured data objects based on the device access status.

3. The system according to claim 1, characterized in that, The data acquisition module includes: a configurable acquisition unit for periodically acquiring operational status data of laboratory equipment according to a predefined acquisition strategy; a real-time processing unit for processing the acquired raw operational status data in real time to obtain processed operational status data; and a data distribution unit for pushing the processed operational status data to the message middleware of the Internet of Things platform in real time for the monitoring and analysis module to subscribe to and consume.

4. The system according to claim 1, characterized in that, The monitoring and analysis module includes: a data analysis engine, used to receive the operating status data, perform real-time comparison and statistical analysis of the operating status data based on a preset equipment operating benchmark model, and obtain anomaly and performance deviation identification results; a health assessment unit, used to call a health calculation model matching the laboratory equipment type according to the anomaly and performance deviation identification results, to perform quantitative assessment of the laboratory equipment and generate health status assessment results; and an intelligent early warning unit, used to identify and predict progressive failures and / or critical risks in the early stage based on the health status assessment results through a machine learning model, and generate fault early warning information.

5. The system according to claim 4, characterized in that, The intelligent early warning unit specifically includes: a progressive fault identification and prediction subunit, used to predict the degradation trend of laboratory equipment performance based on historical sequence data of the health status assessment results through a machine learning model, so as to identify abnormal degradation trajectories, and predict the probability and time of failure in a specific future period based on the identification results; and a critical risk identification and prediction subunit, used to perform real-time pattern recognition and multi-dimensional correlation analysis on preset operating parameter combinations based on the real-time operating status data output by the data analysis engine, generate risk judgment results characterizing the degree of operational abnormality, and determine whether the laboratory equipment is in or about to enter a critical risk state based on the risk judgment results.

6. The system according to claim 5, characterized in that, The input to the progressive fault identification and prediction subunit is the historical sequence of equipment health status assessment results and corresponding timestamps, and the output is the health score prediction sequence within a future preset prediction window. Based on the type of target laboratory equipment, the importance of core components, and historical failure data, a preset degradation threshold is set differently. The preset degradation threshold is compared with the health score prediction sequence to determine the predicted failure time. Furthermore, the failure probability is obtained through comprehensive quantitative evaluation based on the historical prediction consistency of the time-series degradation prediction model and the fluctuation range of the health score prediction sequence.

7. The system according to claim 4 or 5, characterized in that, The fault warning information includes the fault impact degree; the fault impact degree is used to quantitatively characterize the comprehensive impact of potential faults on experimental continuity, equipment safety and operation and maintenance costs. The intelligent early warning unit is used to obtain the fault impact degree based on a three-dimensional comprehensive evaluation, including: the first dimension, which represents the fault type determined by matching abnormal features with a fault mode library; The second dimension represents the functional importance level of the target device in the experimental process; the third dimension represents the preset attribute information of the current experimental task associated with the target device, which includes at least one of the following: task urgency, importance level, progress stage, and the value of associated samples or data.

8. The system according to claim 4 or 5, characterized in that, The fault warning information includes possible root causes; the intelligent warning unit is used to perform matching analysis between abnormal features based on operating status data and a preset fault mode library to determine the possible root causes; wherein, the fault mode library is stored in a structured manner and integrates equipment manufacturer manuals, historical operation and maintenance data and industry case data to establish the correspondence between equipment components, abnormal features and historical fault root causes.

9. The system according to claim 1, characterized in that, The operation and maintenance management module includes: an operation and maintenance task generation unit, used to calculate the operation and maintenance risk score based on the equipment health and fault impact output by the monitoring and analysis module, and determine the task type, task priority and task time limit requirements of the operation and maintenance task according to the operation and maintenance risk score, and generate structured operation and maintenance tasks; and a resource intelligent scheduling unit, used to convert the structured operation and maintenance tasks into a set of scheduling constraints including skill matching, arrival time, spare parts inventory and task time limit constraints, and output scheduling instructions based on a multi-objective optimization algorithm.

10. The system according to claim 9, characterized in that, The intelligent resource scheduling unit is used to schedule operation and maintenance resources based on a multi-objective optimization model. The multi-objective optimization model includes at least objective functions for minimizing the expected downtime of equipment, minimizing the arrival time of operation and maintenance personnel, and minimizing the cost of spare parts consumption. Under the condition of satisfying the constraints of skill matching, spare parts inventory, and task time limit, it outputs the optimal combination scheduling instructions.

Images