Laboratory equipment control system and method based on data processing

Abstract

The invention relates to the technical field of equipment control, and discloses a laboratory equipment control system and method based on data processing, and the system comprises a multi-scale feature analysis module, a topological manifold evolution module, a fiber cross section solving module, a singular point standard resolution module, a leaf-shaped structure discretization module and a semantic instruction coding module. Analyzing the original data to obtain multi-level stability features; carrying out topological structure evolution on the dynamic operation state to obtain a state evolution manifold; performing relation mapping on the state evolution manifold, and performing constraint derivation on the fiber bundle structure to obtain a continuous control section; performing abnormal point digestion on the continuous control section to obtain an ideal control manifold; carrying out leafy structure segmentation on the ideal control manifold, and carrying out cross discretization on the basic leafy structure to obtain a control action sequence; performing semantic coding on the control action sequence to obtain an operation instruction set; according to the invention, the reference information generation efficiency based on artificial intelligence and smart home can be improved.

Description

Technical Field

[0001] This invention relates to the field of equipment control technology, and in particular to a laboratory equipment control system and method based on data processing. Background Technology

[0002] Existing laboratory equipment control systems suffer from a single analytical dimension in the data processing stage. This makes it impossible to perform multi-scale in-depth mining of raw equipment data, and it is difficult to accurately capture the multi-level stability characteristics during equipment operation. This leads to a bias in the understanding of the dynamic operating status of the equipment, and fails to provide comprehensive and reliable status support for the formulation of control strategies, thereby affecting the scientific nature and pertinence of control decisions.

[0003] Existing technologies lack a precise adaptation mechanism to the state evolution law during the construction of control manifolds and the generation of control commands. This makes it difficult to effectively handle abnormal singularities in the control process. Furthermore, the discretization and semantic encoding of control action sequences lack systematicity, resulting in insufficient continuity of control cross-sections and poor logical coherence of control actions. Ultimately, this leads to low executability and reliability of equipment operation commands, failing to meet the high-precision and stable control requirements of laboratory equipment. Therefore, how to improve the control efficiency of a data processing-based laboratory device has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a data processing-based laboratory equipment control system and method to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a laboratory equipment control system based on data processing, characterized in that the system includes a multi-scale feature analysis module, a topological manifold evolution module, a fiber cross-section solution module, a singularity canonical resolution module, a foliate structure discretization module, and a semantic instruction encoding module, wherein: The multi-scale feature parsing module is used to perform multi-scale parsing on the raw data of the target device to obtain the multi-level stability features of the target device. The topology manifold evolution module is used to perform topology evolution on the dynamic operating state of the target device based on multi-level stability characteristics, so as to obtain the state evolution manifold of the target device. The fiber cross section solving module is used to map the correlation relationship of the state evolution manifold based on the preset experimental procedure requirements, and to derive the constraint of the fiber bundle structure of the mapping relationship to obtain the continuous control cross section of the fiber bundle structure. The singularity canonical resolution module is used to resolve outliers in a continuous control section to obtain the ideal control manifold of the continuous control section. The leaf structure discretization module is used to perform leaf structure segmentation on the ideal control manifold to obtain the basic leaf structure of the ideal control manifold, and to perform cross-sectional discretization on the basic leaf structure to obtain the basic control action sequence of the basic leaf structure. The semantic instruction encoding module is used to perform formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device.

[0006] In a preferred embodiment, when the multi-scale feature parsing module performs multi-scale parsing on the original data of the target device to obtain the multi-level stability features of the target device, it is specifically used for: The original data of the target device is subjected to time-frequency joint decomposition to obtain a multi-scale representation of the original data; Cross-scale fusion of multi-scale representations yields the fused features of the target device. By structuring the fusion features, multi-level stability features of the target device are obtained.

[0007] In a preferred embodiment, when the topology manifold evolution module performs topology evolution on the dynamic operating state of the target device based on multi-level stability characteristics to obtain the state evolution manifold of the target device, it is specifically used for: Based on multi-level stability characteristics, the dynamic operating state of the target device is embedded in a high-dimensional phase space to obtain the phase space point cloud of the dynamic operating state. Lifecycle tracking of multi-scale hole structures in phase space point clouds yields a dynamic persistent topological map. Based on the topological persistent graph, the phase space point cloud is reconstructed into a manifold to obtain a preliminary state surface of the dynamic running state. Based on the boundary conditions with multi-level stability characteristics, the boundary contraction of the state surface prototype is performed to obtain the state evolution manifold of the target device.

[0008] In a preferred embodiment, when the topology manifold evolution module performs manifold reconstruction of the phase space point cloud based on the topological persistent graph to obtain a preliminary state surface of the dynamic running state, it is specifically used for: The key persistence intervals of the dimensional features of the topological persistent graph are quantized to obtain the key lifecycle parameter set of the topological persistent graph; Spatial statistics are fused from the phase space point cloud corresponding to the dimensional features to obtain the distribution correlation factor of the phase space point cloud; Based on the key lifecycle parameter set, the optimal reconstruction scale factor of the phase space point cloud is calculated; Based on the optimal reconstruction scale factor, the Riemannian degree is defined for the phase space point cloud to obtain the weighted phase space metric of the phase space point cloud; Based on weighted phase space metric, local spatial alignment and fusion of phase space point clouds are performed to obtain a preliminary state surface of dynamic operation.

[0009] In a preferred embodiment, when the fiber cross-section solving module performs correlation mapping on the state evolution manifold based on preset experimental procedures and derives constraints on the fiber bundle structure of the mapped relationship to obtain the continuous control cross-section of the fiber bundle structure, it is specifically used for: The pre-set experimental procedure requirements are logically decomposed to obtain the set of process constraints required by the experimental procedure. Based on the state evolution manifold, the set of process constraints is filtered for compatibility to obtain a feasible subset of constraints for the state evolution manifold. Based on the state evolution manifold, the constraint space is projected onto the feasible constraint subset to obtain the fiber bundle structure of the state evolution manifold; Connectivity path screening is performed on fiber bundle structures to obtain a set of candidate through paths for fiber bundle structures; The set of candidate through paths is evaluated for its resistance to disturbance, and the compliant paths after evaluation are coordinated and integrated to obtain the continuous control section of the fiber bundle structure.

[0010] In a preferred embodiment, when the fiber cross-section solving module performs constraint space projection on a feasible subset of constraints based on the state evolution manifold to obtain the fiber bundle structure of the state evolution manifold, it is specifically used for: Geometric discretization of the state evolution manifold yields a sample mesh of the state evolution manifold; Tangent bundle constraints are assigned to the sample point mesh to obtain the tangent space specification frame of the sample point mesh; Based on the tangent space standard frame, the feasible constraint subset is orthogonally decomposed to obtain the tangent projection vector and conormal component of the feasible constraint subset; Based on the tangential projection vector and the state evolution manifold, the overall coordination factor of the constraint projection is calculated; Based on the overall coordination factor, the fiber directivity of the tangential projection vector is tuned to obtain the standard fiber direction field of the tangential projection vector; By structurally closing the normed fiber orientation field and the conormal component, a fiber bundle structure of state evolution manifold is obtained.

[0011] In a preferred embodiment, when the singularity canonical resolution module performs outlier resolution on a continuous control section to obtain the ideal control manifold of the continuous control section, it is specifically used for: Local structural deformation is performed on the singularity neighborhood of the continuous control section to obtain the normalized coordinate expression of the singularity neighborhood; Based on the experimental procedure requirements, a constrained isomorphic mapping is applied to the normalized coordinate representation to obtain a corrected local representation of the singularity neighborhood. By geometrically merging the modified local representation with the continuous control section, an ideal control manifold with the continuous control section is obtained.

[0012] In a preferred embodiment, when the foliate structure discretization module performs foliate structure segmentation on the ideal control manifold to obtain the basic foliate structure of the ideal control manifold, and performs cross-sectional discretization on the basic foliate structure to obtain the basic control action sequence of the basic foliate structure, it is specifically used for: Actively perform simulated path extraction on the ideal control manifold to obtain the core motion path segment of the ideal control manifold; Based on the experimental procedure requirements, supplementary motion path planning is performed on the ideal control manifold to obtain auxiliary motion path segments of the ideal control manifold. By integrating the core action path segment and the auxiliary action path segment with temporal logic, the basic leaf structure of the ideal control manifold is obtained. The independent execution phases of the basic leaf-shaped structure are standardized and segmented to obtain the action primitives of the independent execution phases; Logically arrange the action primitives to obtain the basic control action sequence of the basic leaf structure.

[0013] In a preferred embodiment, when the semantic instruction encoding module performs formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device, it is specifically used for: Context semantic binding is performed on the basic control action sequence to obtain the typed semantic sequence of the target device; By integrating the structural paradigms of the typified semantic sequences, an abstract syntax tree representation of the typified semantic sequences is obtained; Structural encoding is performed on the abstract syntax tree representation to obtain the standard instruction set of the abstract syntax tree representation; Based on the instruction format of the target device, the standard instruction set is encapsulated for protocol consistency to obtain the executable operation instruction set of the target device.

[0014] To address the above problems, the present invention also provides a data processing-based laboratory equipment control method, the method comprising: S01. Perform multi-scale analysis on the raw data of the target device to obtain the multi-level stability characteristics of the target device; S02. Based on the multi-level stability characteristics, the dynamic operating state of the target device is subjected to topological structure evolution to obtain the state evolution manifold of the target device. S03. Based on the preset experimental procedure requirements, the correlation relationship of the state evolution manifold is mapped, and the fiber bundle structure of the mapping relationship is constrained and derived to obtain the continuous control section of the fiber bundle structure. S04. Eliminate outliers on the continuous control section to obtain the ideal control manifold of the continuous control section; S05. Perform folio segmentation on the ideal control manifold to obtain the basic folio structure of the ideal control manifold, and perform cross-sectional discretization on the basic folio structure to obtain the basic control action sequence of the basic folio structure. S06. Perform formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention achieves accurate multi-level analysis of the original data of the target device through a multi-scale feature analysis module, and completes the topological structure evolution of the dynamic operating state by combining it with a topology manifold evolution module. It can accurately capture the stability characteristics and state evolution laws of the device operation, provide high-quality data and state support for subsequent control decisions, significantly improve the adaptability and accuracy of control strategies, and ensure the stability and controllability of the device's operating state.

[0016] 2. This invention achieves optimized construction of the control manifold through modules such as fiber cross-section solving and singularity normalization elimination. It combines leaf structure discretization and semantic instruction encoding to complete the accurate generation and normalization encoding of control action sequences, effectively eliminating abnormal interference in the control process, ensuring the continuity and logic of control actions, improving the effectiveness and executability of the operation instruction set, and enhancing the automation level and operational reliability of laboratory equipment control. Attached Figure Description

[0017] Figure 1 A system architecture diagram of a data processing-based laboratory equipment control system provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating a data processing-based laboratory equipment control method according to an embodiment of the present invention.

[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments belong to some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0021] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0022] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0023] In practice, the server-side equipment deployed in a data-processing-based laboratory equipment control system may consist of one or more devices. This data-processing-based laboratory equipment control system can be implemented as: a business instance, a virtual machine, or hardware devices. For example, the data-processing-based laboratory equipment control system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, this data-processing-based laboratory equipment control system can be understood as software deployed on a cloud node, used to provide a data-processing-based laboratory equipment control system to various user terminals. Alternatively, the data-processing-based laboratory equipment control system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Alternatively, the data-processing-based laboratory equipment control system can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide the data-processing-based laboratory equipment control system to various user terminals.

[0024] In terms of implementation, the data processing-based laboratory equipment control system and the user terminal are mutually compatible. That is, if the data processing-based laboratory equipment control system is implemented as an application installed on a cloud service platform, then the user terminal is implemented as a client that establishes a communication connection with the application; or if the data processing-based laboratory equipment control system is implemented as a website, then the user terminal is implemented as a webpage; or if the data processing-based laboratory equipment control system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0025] like Figure 1 The diagram shown is a system architecture diagram of a laboratory equipment control system based on data processing provided in an embodiment of the present invention.

[0026] The data processing-based laboratory equipment control system 10 of this invention can be located on a cloud server. In terms of implementation, it can function as one or more service devices, or as an application installed on the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the data processing-based laboratory equipment control system 10 may include a multi-scale feature analysis module 11, a topological manifold evolution module 12, a fiber cross-section solving module 13, a singularity canonical resolution module 14, a foliate structure discretization module 15, and a semantic instruction encoding module 16. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, stored in the electronic device's memory.

[0027] In this embodiment of the invention, in the data processing-based laboratory equipment control system, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the data processing-based laboratory equipment control system provided by this embodiment of the invention, the applicable scope of the data processing-based laboratory equipment control system architecture can be adjusted by adding modules and directly calling them without modifying the program code, achieving cluster-based horizontal expansion to quickly and flexibly expand the data processing-based laboratory equipment control system. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0028] The following describes the various components and specific workflows of a data processing-based laboratory equipment control system, using specific embodiments as examples: The multi-scale feature parsing module 11 is used to perform multi-scale parsing on the original data of the target device to obtain the multi-level stability features of the target device. In this embodiment of the invention, when the multi-scale feature parsing module performs multi-scale parsing on the original data of the target device to obtain the multi-level stability features of the target device, it is specifically used for: The original data of the target device is subjected to time-frequency joint decomposition to obtain a multi-scale representation of the original data; Cross-scale fusion of multi-scale representations yields the fused features of the target device. By structuring the fusion features, multi-level stability features of the target device are obtained.

[0029] The raw data of the target device is decomposed simultaneously in terms of time and frequency dimensions. First, the raw data is divided into continuous time segments in chronological order. Then, the frequency components contained in each time segment are analyzed. Through the correspondence between time and frequency, the raw data is transformed into a set of feature segments under different time scales and different frequency scales. These sets of feature segments together constitute a multi-scale representation of the raw data.

[0030] For the feature segments of each scale in the obtained multi-scale representation, establish the correlation mapping between scales, and mutually verify and supplement the feature segments representing the same equipment operation attributes at different scales. Eliminate duplicate feature information in each scale, retain the feature content with unique representational significance at each scale, and then organically integrate these filtered and integrated feature contents to form a fusion feature that can comprehensively reflect the operating status of the target equipment.

[0031] The obtained fused features are hierarchically divided. Based on the importance and correlation logic of the equipment operation stability related attributes represented by the features, the fused features are divided into different levels. Each level corresponds to a set of features related to equipment stability. The features within each level are then sorted out in an orderly manner to form a clear logical relationship between the features of each level, and finally a multi-level stability feature of the target equipment is formed.

[0032] The beneficial effect is that by simultaneously decomposing the original data into multi-scale representations through time and frequency dimensions, and then integrating them through inter-scale correlation mapping to form fusion features, and finally classifying and sorting them according to the stability-related attribute hierarchy to form multi-level stability features, it can fully explore the effective information at different scales in the original data, comprehensively and accurately reflect the target equipment's operating status and stability-related attributes, and provide comprehensive and reliable feature support for subsequent dynamic operating status analysis and control strategy formulation based on these features.

[0033] The topology manifold evolution module 12 is used to perform topology evolution on the dynamic operating state of the target device based on multi-level stability characteristics, so as to obtain the state evolution manifold of the target device. In this embodiment of the invention, when the topology manifold evolution module performs topology evolution on the dynamic operating state of the target device based on multi-level stability characteristics to obtain the state evolution manifold of the target device, it is specifically used for: Based on multi-level stability characteristics, the dynamic operating state of the target device is embedded in a high-dimensional phase space to obtain the phase space point cloud of the dynamic operating state. Lifecycle tracking of multi-scale hole structures in phase space point clouds yields a dynamic persistent topological map. Based on the topological persistent graph, the phase space point cloud is reconstructed into a manifold to obtain a preliminary state surface of the dynamic running state. Based on the boundary conditions with multi-level stability characteristics, the boundary contraction of the state surface prototype is performed to obtain the state evolution manifold of the target device.

[0034] When the topological manifold evolution module performs manifold reconstruction of the phase space point cloud based on the topological persistent graph to obtain a preliminary state surface of the dynamic running state, it is specifically used for: The key persistence intervals of the dimensional features of the topological persistent graph are quantized to obtain the key lifecycle parameter set of the topological persistent graph; Spatial statistics are fused from the phase space point cloud corresponding to the dimensional features to obtain the distribution correlation factor of the phase space point cloud; Based on the key lifecycle parameter set, the optimal reconstruction scale factor of the phase space point cloud is calculated; Based on the optimal reconstruction scale factor, the Riemannian degree is defined for the phase space point cloud to obtain the weighted phase space metric of the phase space point cloud; Based on weighted phase space metric, local spatial alignment and fusion of phase space point clouds are performed to obtain a preliminary state surface of dynamic operation.

[0035] Based on the hierarchical stability information of the target device's operating state contained in the multi-level stability features, the state parameters of the target device at each moment during dynamic operation are combined with the corresponding level of stability features. Each set of combined information is then mapped to a node in a high-dimensional space. Each node uniquely corresponds to the operating state of the device at a certain moment. The nodes corresponding to all moments during dynamic operation are arranged in chronological order to form a phase space point cloud of the dynamic operating state.

[0036] The system comprehensively tracks hole structures of different scales in phase space point clouds, identifies the initial position of each hole structure in phase space and the corresponding equipment operating state, records the morphological change process of the hole structure in space and the corresponding equipment state evolution stage during the change process, clarifies the position where each hole structure disappears and the corresponding stable state of the equipment, and organizes and summarizes the complete process information of all hole structures from appearance to disappearance to form a dynamic operating state topological persistent map.

[0037] The duration segments corresponding to the features of each dimension in the topology persistence graph are analyzed to screen out the duration intervals that have a key impact on the dynamic operating state evolution of the target device. These key intervals correspond to the stages in which the operating state of the device changes significantly. The start position, end position, duration, and corresponding device state characteristics of each key interval are integrated to form a set of key lifecycle parameters for the topology persistence graph.

[0038] For the phase space point cloud portion corresponding to the features of each dimension of the topological persistent graph, spatial statistical information such as the distribution density of the point cloud in high-dimensional space, the relative distance between points, and the degree of aggregation of point groups are extracted. This statistical information is cross-validated and integrated, and duplicate and meaningless statistical content is removed. The core information that can reflect the spatial distribution law of the point cloud is retained to form the distribution correlation factor of the phase space point cloud.

[0039] Based on the distribution patterns of phase space point clouds reflected by the persistence characteristics and distribution correlation factors of each key interval in the key lifecycle parameter set, a comprehensive judgment is made on the scale standard that best matches the actual operating state evolution trend of the target equipment after the phase space point cloud reconstruction. This scale standard needs to take into account both the lifecycle characteristics of the hole structure and the spatial distribution characteristics of the point cloud. Therefore, the optimal reconstruction scale factor of the phase space point cloud is determined. The formula for calculating the optimal reconstruction scale factor is as follows: ; In the formula, The optimal reconstruction scale factor. For the domain of the critical lifecycle parameter set, For the first in the topological persistent graph Termination scale of a topological feature For the first in the topological persistent graph The initial scale of a topological feature The pre-defined characteristic persistence option weighting coefficient, It is a natural exponential function. The preset initial scale suppression coefficient, The preset termination delay enhancement coefficient, This represents the maximum value of all terminating scales in the topological persistent graph. It is the natural logarithm function. For the first in the topological persistent graph Distribution correlation factor of each topological feature This represents the maximum value of the spatial distribution density correlation factor.

[0040] Based on the optimal reconstruction scale factor, a distance calculation rule is defined between points in phase space. The distance must reflect the correlation between the corresponding equipment operating status. At the same time, each point in the phase space point cloud is assigned a weight value. The magnitude of the weight value corresponds to the importance of the equipment operating status represented by the point. The weight value and the distance calculation rule together constitute the weighted phase space metric of the phase space point cloud.

[0041] Based on the distance rules and weight allocation standards defined by the weighted phase space metric, the relative positions of each point in the phase space point cloud are adjusted so that points with high weight values ​​are more closely distributed in space, and the spatial relationship between points can accurately reflect the correlation logic of the equipment's operating status. All points after the position adjustment are integrated to form a continuous and smooth surface, which is the prototype of the state surface of the dynamic operating status.

[0042] The boundary constraint information of the target device's operating state contained in the multi-level stability features is extracted. This information clarifies the stable range of the device's operation and the limit threshold of state changes. Based on this boundary constraint information, the edge part of the state surface prototype is adjusted, and the area in the surface that exceeds the boundary constraint range is shrunk so that the edge of the surface completely fits the range specified by the boundary constraint information, and finally the state evolution manifold of the target device is obtained.

[0043] The domain of the key lifecycle parameter set is derived from the coverage of these intervals after quantizing the key persistence intervals of the topology persistent graph's dimensional features. The termination and starting scales of a topological feature are the scales at which the feature disappears and appears, respectively, while tracking the lifecycle of multi-scale hole structures in the phase space point cloud. The feature persistence factor, starting scale suppression factor, and termination delay enhancement factor are pre-set values ​​directly applied to the calculations. The maximum value of all termination scales in the topological persistence graph is the largest value selected after statistically analyzing all topological feature termination scales. The distribution correlation factor of each topological feature is the result obtained by fusing spatial statistics of the corresponding phase space point cloud. The maximum value of the spatial distribution density correlation factor is the maximum value selected after statistically analyzing all distribution correlation factors.

[0044] This content is used to determine the optimal reconstruction scale factor. By integrating the continuous information of topological features in the key life cycle parameter set, the impact information of the start and end scales, and the distribution correlation factor information corresponding to the topological features, the scale standard that best fits the actual operating state evolution law of the device after the phase space point cloud is reconstructed is obtained.

[0045] When the difference between the termination scale and the starting scale of a topological feature increases, its weight in the calculation increases, and its influence on the optimal reconstruction scale factor strengthens. When the starting scale increases, the corresponding suppression effect increases, the weight of the feature decreases, and its influence weakens. When the termination scale is closer to the maximum value of all termination scales, the corresponding enhancement effect increases, the weight of the feature increases, and its influence strengthens. At the same time, when the distribution correlation factor of the topological feature is closer to the maximum value of the spatial distribution density correlation factor, the corresponding logarithmic term value increases, and its positive influence on the optimal reconstruction scale factor also strengthens.

[0046] The beneficial effect is that the dynamic operating state of the target equipment is embedded into a high-dimensional phase space to form a phase space point cloud based on multi-level stability characteristics. By tracking the life cycle of multi-scale hole structures in the point cloud, a topological persistence graph is formed. Then, the optimal reconstruction scale factor is determined by quantifying key persistence intervals and fusing spatial statistics. Based on this, a weighted phase space metric is defined and the fused point cloud is aligned to form a preliminary state surface. Finally, the state evolution manifold is obtained by combining boundary conditions and shrinking. This can accurately capture the topological evolution law of the dynamic operating state of the equipment. The constructed state evolution manifold can truly reflect the changing trend of the equipment's operating state, providing an accurate and reliable state basis for subsequent control links.

[0047] By accurately acquiring the required information through processes such as topological persistent graph analysis and hole structure lifecycle tracking, and combining preset coefficients and statistical extreme values, this content can integrate the continuous information of topological features, scale influence information, and distribution correlation information to determine the optimal reconstruction scale factor that best fits the actual operating state evolution law of the equipment. Furthermore, as the relevant attributes of topological features change, this content can reasonably adjust the degree of influence of each feature on the scale factor, making the obtained optimal reconstruction scale factor more accurately adapt to actual needs, and providing a reliable scale basis for the effective reconstruction of phase space point clouds.

[0048] The fiber cross section solving module 13 is used to perform correlation mapping on the state evolution manifold based on the preset experimental procedure requirements, and to perform constraint derivation on the fiber bundle structure of the mapping relationship to obtain the continuous control cross section of the fiber bundle structure. In this embodiment of the invention, when the fiber cross-section solving module performs correlation mapping on the state evolution manifold based on preset experimental procedures and derives the constraints of the mapped fiber bundle structure to obtain the continuous control cross-section of the fiber bundle structure, it is specifically used for: The pre-set experimental procedure requirements are logically decomposed to obtain the set of process constraints required by the experimental procedure. Based on the state evolution manifold, the set of process constraints is filtered for compatibility to obtain a feasible subset of constraints for the state evolution manifold. Based on the state evolution manifold, the constraint space is projected onto the feasible constraint subset to obtain the fiber bundle structure of the state evolution manifold; Connectivity path screening is performed on fiber bundle structures to obtain a set of candidate through paths for fiber bundle structures; The set of candidate through paths is evaluated for its resistance to disturbance, and the compliant paths after evaluation are coordinated and integrated to obtain the continuous control section of the fiber bundle structure.

[0049] The fiber cross-section solving module, when performing constraint space projection on a feasible subset based on the state evolution manifold to obtain the fiber bundle structure of the state evolution manifold, is specifically used for: Geometric discretization of the state evolution manifold yields a sample mesh of the state evolution manifold; Tangent bundle constraints are assigned to the sample point mesh to obtain the tangent space specification frame of the sample point mesh; Based on the tangent space standard frame, the feasible constraint subset is orthogonally decomposed to obtain the tangent projection vector and conormal component of the feasible constraint subset; Based on the tangential projection vector and the state evolution manifold, the overall coordination factor of the constraint projection is calculated; Based on the overall coordination factor, the fiber directivity of the tangential projection vector is tuned to obtain the standard fiber direction field of the tangential projection vector; By structurally closing the normed fiber orientation field and the conormal component, a fiber bundle structure of state evolution manifold is obtained.

[0050] The pre-set experimental procedure requirements are logically decomposed. According to the inherent logic of the experimental execution sequence, core control indicators, and equipment status constraints, the experimental procedure requirements are broken down into multiple specific and clear constraint items. Each constraint item clearly defines the corresponding operating procedures, state parameter ranges, execution timing requirements, and safety boundary conditions. All constraint items are logically classified and integrated to form the process constraint condition set of the experimental procedure requirements.

[0051] Based on the dynamic operating state range and evolution law of the target equipment represented by the state evolution manifold, each constraint item in the process constraint condition set is checked one by one. It is determined whether the parameter range and execution requirements specified by each item match the state coverage range and evolution trend of the state evolution manifold. Constraint items that are incompatible with the operating characteristics of the state evolution manifold are eliminated, and constraint items that can adapt to the state evolution manifold and meet the actual operating requirements of the equipment are retained. These retained constraint items together constitute the feasible constraint subset of the state evolution manifold.

[0052] The state evolution manifold is geometrically discretized, and the overall region of the state evolution manifold is divided into multiple small spatial units according to uniform spatial intervals. A sample point that precisely corresponds to the position of the manifold is determined at the center of each spatial unit. All sample points are arranged in an orderly manner according to the spatial structure and geometric shape of the state evolution manifold to form a sample point grid of the state evolution manifold covering the entire manifold region.

[0053] Tangential constraints are assigned to the sample point mesh. For each sample point in the sample point mesh, the allowable state change direction and tangential movement range at the sample point are set based on the operating state characteristics of the equipment at the corresponding location. The tangential constraint rules for each sample point are clarified. The tangential constraint rules of all sample points correspond one-to-one with the spatial position of the sample points, and together they constitute the tangential space specification frame of the sample point mesh.

[0054] Based on the tangent space specification frame, the feasible constraint subset is orthogonally decomposed. Taking the tangent direction defined by the tangent space specification frame as the reference, each constraint in the feasible constraint subset is decomposed into two mutually perpendicular parts. The part parallel to the tangent space specification frame direction is the tangent projection vector of the feasible constraint subset, and the part perpendicular to the tangent space specification frame direction is the conormal component of the feasible constraint subset. The decomposition process ensures that the vector relationship between the two parts fully meets the orthogonality requirement.

[0055] Based on the tangential projection vector and the state evolution manifold, the direction and intensity information of the tangential projection vector at all sample points, as well as the geometric and state continuity characteristics of the state evolution manifold at the corresponding sample point locations, are integrated to comprehensively judge the degree of fit between the tangential projection vector and the state evolution manifold, thus obtaining the overall coordination factor of the constraint projection that can characterize the overall coordination of the constraint projection. The formula for calculating the overall coordination factor is as follows: ; In the formula, As an overall coordinating factor, For a state evolution manifold, These are constraints for a feasible subset of constraints. For feasible constraint subsets, To constrain At the sampling point Tangential projection vector at the location Let be the square of the Euclidean norm. It is a natural exponential function. For the state evolution manifold at the sample point Gaussian curvature at that point These are samples on the state evolution manifold.

[0056] Based on the overall coordination factor, the fiber orientation of the tangential projection vector is tuned. According to the degree of fit reflected by the overall coordination factor, the direction and intensity of the tangential projection vector at each sample point are adjusted so that the direction of the adjusted tangential projection vector is more in line with the construction requirements of the fiber structure. At the same time, it is ensured that the direction of the tangential projection vector of adjacent sample points remains consistent. All the adjusted tangential projection vectors are combined to form the standard fiber orientation field of the tangential projection vector.

[0057] By structurally closing the canonical fiber orientation field and the conormal component, the tangential structure represented by the canonical fiber orientation field and the normal structure represented by the conormal component are spatially integrated, so that the two form a complementary relationship in space, and a complete and continuous spatial structure is constructed. This spatial structure is the fiber bundle structure of the state evolution manifold.

[0058] The fiber bundle structure is screened for connectivity paths by traversing all possible paths within the fiber bundle structure and determining whether each path can run uninterruptedly from the start end to the end end of the fiber bundle structure. At the same time, it is checked whether each path strictly meets all the constraint requirements of the feasible constraint subset. Paths that simultaneously satisfy both connectivity and constraint compliance are selected, and these paths together constitute the candidate connectivity path set of the fiber bundle structure.

[0059] The anti-disturbance capability of the candidate through path set is evaluated. The simulation of the state fluctuations and external environmental interference that may occur during the actual operation of the target equipment is carried out. The stability of each path in the candidate through path set under the interference scenario is tested. It is observed whether the path will break or deviate from the constraint range. Paths with insufficient anti-disturbance capability are eliminated, and compliant paths that can operate stably are retained. Then, these compliant paths are coordinated and integrated in terms of timing and logic to eliminate the connection breakpoints between paths, so that the paths form a continuous and uninterrupted transition, and finally the continuous control section of the fiber bundle structure is obtained.

[0060] The state evolution manifold is the result of topological evolution of the target device's dynamic operating state. The feasible constraint subset is a set of constraints formed by logically decomposing the pre-defined experimental requirements and then performing compatibility filtering based on the state evolution manifold. The constraint conditions of the feasible constraint subset are the specific constraint entries within this set. The tangential projection vector of the constraint at the sample point is the portion parallel to the tangent space specification frame direction obtained after orthogonal decomposition of the feasible constraint subset based on the tangent space specification frame. The Gaussian curvature of the state evolution manifold at the sample point is the result of geometric analysis of the state evolution manifold, clarifying the degree of manifold curvature at each sample point location. A sample point on the state evolution manifold is each node in the sample point mesh obtained after geometrically discretizing the state evolution manifold.

[0061] This content is used to determine the overall coordination factor of constraint projection. By integrating the tangential projection vector information of constraints at each sample point on the state evolution manifold with the Gaussian curvature information of the manifold at the corresponding sample point, a result that can characterize the overall fit and coordination between constraints and the state evolution manifold during the constraint projection process is obtained.

[0062] When the squared Euclidean norm of the tangential projection vector of constraints at a sample point increases, the corresponding correlation term at that sample point increases, and its positive impact on the overall coordination factor strengthens. Conversely, when the Gaussian curvature of the state evolution manifold at a sample point increases, the corresponding natural exponential function term decreases, and the influence of the correlation term at that sample point on the overall coordination factor weakens. When the sum of the squared Euclidean norms of the tangential projection vectors of multiple constraints at a sample point increases, the correlation term at the corresponding sample point increases, and the value of the overall coordination factor increases accordingly. When the Gaussian curvature of most samples on the state evolution manifold is small, the corresponding natural exponential function term is generally large, and the value of the overall coordination factor increases accordingly.

[0063] The beneficial effects are as follows: by logically decomposing and compatibility filtering the requirements of the preset experimental procedure, a feasible subset of constraints that fit the state evolution manifold is obtained. Then, through a series of processes such as state evolution manifold discretization, tangent bundle constraint allocation, and orthogonal decomposition, a fiber bundle structure is formed. Subsequently, through connected path screening and disturbance resistance assessment, compliant paths are coordinated and integrated to obtain a continuous control section. This ensures that the constraints are accurately matched with the equipment operating state. The constructed fiber bundle structure is reasonable and stable, and the formed continuous control section has good anti-interference ability and continuity, providing a precise and reliable control path basis for the generation of control commands for the target equipment.

[0064] By accurately obtaining the required information from processes such as topological evolution of the state-evolving manifold and decomposition and filtering of experimental procedures, this content can integrate the tangential projection vector information of constraints on the state-evolving manifold with the Gaussian curvature information of the manifold. It can determine the overall coordination factor between constraints and the state-evolving manifold during the constraint projection process. At the same time, as the tangential projection vector, Gaussian curvature and other related factors change, their influence on the overall coordination factor can be reasonably adjusted, so that the obtained overall coordination factor can accurately characterize the fit and coordination between constraints and the state-evolving manifold, providing a reliable coordination basis for the subsequent construction of fiber bundle structures.

[0065] The singularity canonical resolution module 14 is used to resolve anomalies in the continuous control section to obtain the ideal control manifold of the continuous control section. In this embodiment of the invention, when the singularity canonical resolution module performs outlier resolution on a continuous control section to obtain the ideal control manifold of the continuous control section, it is specifically used for: Local structural deformation is performed on the singularity neighborhood of the continuous control section to obtain the normalized coordinate expression of the singularity neighborhood; Based on the experimental procedure requirements, a constrained isomorphic mapping is applied to the normalized coordinate representation to obtain a corrected local representation of the singularity neighborhood. By geometrically merging the modified local representation with the continuous control section, an ideal control manifold with the continuous control section is obtained.

[0066] The singularity on the continuous control section is located, and a neighborhood region covering the influence range of the singularity is delineated with the singularity as the center. The local structure within the neighborhood region is adjusted in an orderly manner, and the irregular shape of the structure within the neighborhood is corrected by stretching, translation and compression. The structural abruptness and distortion caused by the singularity are eliminated, and the adjusted neighborhood structure is transformed into a regular and unified coordinate form. These regular and unified coordinate forms together constitute the normalized coordinate expression of the singularity neighborhood.

[0067] Referring to the constraints specified in the pre-set experimental procedures, the normalized coordinate expression of the singularity neighborhood is subjected to isomorphic mapping. Based on the control standards and operating specifications required by the experimental procedures, the coordinate parameters in the normalized coordinate expression are adjusted so that the adjusted coordinate expression fully conforms to the constraint boundaries required by the experimental procedures, ensuring that the mapped coordinate expression can meet the compliance requirements of equipment operation. Thus, the corrected local expression of the singularity neighborhood is obtained.

[0068] By geometrically merging the modified local representation of the singularity neighborhood with the original structure of the continuous control section, a smooth transition interface is constructed in the connection region between the modified local representation and the original structure to eliminate structural discontinuities and differences between the two. This ensures that the fused overall structure maintains continuous and uniform characteristics, allowing the modified local structure and the overall structure of the continuous control section to form an organically unified whole, ultimately obtaining the ideal control manifold of the continuous control section.

[0069] The beneficial effects are as follows: by performing local structural deformation on the singularity neighborhood of the continuous control section, the structural abrupt changes and distortions caused by singularities are effectively eliminated, forming a regular and unified standardized coordinate expression. Then, according to the experimental procedure requirements, constrained isomorphic mapping is performed to ensure that the coordinate expression of the singularity neighborhood fully conforms to the compliance standards of equipment operation, resulting in a precise corrected local expression. Finally, the corrected local expression is geometrically fused with the continuous control section to construct a smooth transition interface to eliminate structural discontinuities, so that the fused overall structure maintains continuous and uniform characteristics. The ideal control manifold of the continuous control section is successfully obtained, which can ensure the integrity and rationality of the control manifold, providing a regular and reliable foundation for subsequent leaf structure discretization and control action sequence generation, and improving the accuracy and stability of the laboratory equipment control process.

[0070] The leaf-shaped structure discretization module 15 is used to perform leaf-shaped structure segmentation on the ideal control manifold to obtain the basic leaf-shaped structure of the ideal control manifold, and to perform cross-sectional discretization on the basic leaf-shaped structure to obtain the basic control action sequence of the basic leaf-shaped structure. In this embodiment of the invention, when the leaf-shaped structure discretization module performs leaf-shaped structure segmentation on the ideal control manifold to obtain the basic leaf-shaped structure of the ideal control manifold, and performs cross-sectional discretization on the basic leaf-shaped structure to obtain the basic control action sequence of the basic leaf-shaped structure, it is specifically used for: Actively perform simulated path extraction on the ideal control manifold to obtain the core motion path segment of the ideal control manifold; Based on the experimental procedure requirements, supplementary motion path planning is performed on the ideal control manifold to obtain auxiliary motion path segments of the ideal control manifold. By integrating the core action path segment and the auxiliary action path segment with temporal logic, the basic leaf structure of the ideal control manifold is obtained. The independent execution phases of the basic leaf-shaped structure are standardized and segmented to obtain the action primitives of the independent execution phases; Logically arrange the action primitives to obtain the basic control action sequence of the basic leaf structure.

[0071] Analyze the overall evolution trend of the ideal control manifold, identify the core direction that plays a dominant role in the control of the target equipment, and extract continuous paths along the core direction that cover the key nodes of equipment control. These continuous paths can carry the main control logic of the ideal control manifold, and finally form the core action path segment of the ideal control manifold.

[0072] Referring to the control flow and operation standards specified in the pre-set experimental procedures, supplementary paths are planned to improve the control logic and connect control nodes for equipment control links and process gaps not covered by the core action path segment. These supplementary paths cooperate with the core action path segment to jointly form the auxiliary action path segment of the ideal control manifold.

[0073] By sorting out the control timing corresponding to the core action path segments, clarifying the execution order and time relationship of each core path, and then accurately embedding the auxiliary action path segments into the reasonable timing position of the core action path segments, the core action path segments and auxiliary action path segments form a hierarchical, sequential and logically unified overall structure. This overall structure is the basic leaf structure of the ideal control manifold.

[0074] The basic leaf-shaped structure is divided into independent control execution stages. Each independent execution stage corresponds to a complete equipment control subtask. According to a unified control standard, each independent execution stage is broken down into the smallest indivisible control unit. These smallest control units can directly correspond to the basic operating behavior of the equipment, thus forming the action primitives of the independent execution stage.

[0075] Based on the control logic required by the experimental procedure and the functional association of each action primitive, the execution order of all action primitives is determined, and possible logical conflicts and timing contradictions between action primitives are eliminated, so that each action primitive is connected in sequence to form a continuous and complete control flow. This control flow is the basic control action sequence of the basic leaf structure.

[0076] The beneficial effects are that by extracting core action path segments from the ideal control manifold and planning auxiliary action path segments, the core logic of equipment control can be accurately anchored and the connection of control links can be improved. Then, through temporal logic integration, a hierarchical and coherent basic leaf structure is formed. Subsequently, the action primitives of the smallest control unit are obtained by standardizing and dividing the independent execution stage. Finally, the conflicts and contradictions between action primitives are eliminated through logic arrangement, forming a continuous and complete basic control action sequence. This can ensure the orderliness and rationality of control actions, provide a logically clear and smoothly connected action basis for subsequent semantic instruction encoding, and improve the standardization and efficiency of laboratory equipment control processes.

[0077] The semantic instruction encoding module 16 is used to perform formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device. In this embodiment of the invention, when the semantic instruction encoding module performs formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device, it is specifically used for: Context semantic binding is performed on the basic control action sequence to obtain the typed semantic sequence of the target device; By integrating the structural paradigms of the typified semantic sequences, an abstract syntax tree representation of the typified semantic sequences is obtained; Structural encoding is performed on the abstract syntax tree representation to obtain the standard instruction set of the abstract syntax tree representation; Based on the instruction format of the target device, the standard instruction set is encapsulated for protocol consistency to obtain the executable operation instruction set of the target device.

[0078] The functional meaning and execution logic of each action in the basic control action sequence are sorted out, and the target device operation scenario, execution conditions and connection relationship with the preceding and following actions are associated with each action. Each action is given a clear contextual semantic attribute, and then the actions with semantic attributes are classified and integrated according to the functional type of the action, so that each action can accurately correspond to its semantic category and execution scenario, and finally the typified semantic sequence of the target device is obtained.

[0079] Referring to the general semantic structure paradigm, the inherent hierarchical relationship of the typified semantic sequence is analyzed. The overall control task of the device at the top layer, the action type grouping in the middle layer, and the specific action semantics at the bottom layer are clarified. A tree structure is constructed according to the top-down hierarchical logic, with the top-level task as the root node, the action type in the middle layer as the branch node, and the specific action semantics at the bottom layer as the leaf node. The subordinate and related semantic relationships between nodes are clearly reflected through branches, thus obtaining the abstract syntax tree representation of the typified semantic sequence.

[0080] Based on the node hierarchy and semantic association rules represented by the abstract syntax tree, each node in the tree is assigned a unique semantic code identifier. The code identifier must reflect the node's hierarchical position and semantic type. Then, all nodes of the abstract syntax tree are traversed in depth-first order, and the code identifier of each node is combined with its corresponding semantic content in an orderly manner to eliminate coding redundancy and semantic conflicts between nodes, forming a set with clear structure, explicit semantics and standardized coding, which is the standard instruction set represented by the abstract syntax tree.

[0081] The inherent instruction format requirements of the target device are analyzed to clarify the field composition, field order, semantic expression, and device-recognizable instruction identifiers of the instructions. Each instruction in the standardized instruction set is then split and reorganized according to the instruction format requirements of the target device. Execution identifiers and format identifiers that the device can recognize are added to ensure that each adjusted instruction fully matches the instruction protocol of the target device in terms of field structure and semantic expression, ultimately yielding the executable operation instruction set of the target device.

[0082] The beneficial effects are as follows: by performing contextual semantic binding on the basic control action sequence, each action is given a clear operating scenario, execution conditions, and connection relationship, forming a typified semantic sequence that accurately corresponds to the semantic category. Then, through structural paradigm integration, a hierarchical abstract syntax tree representation is constructed, clearly sorting out the subordinate and related logic of semantics. Subsequently, the abstract syntax tree is structurally encoded to eliminate redundancy and conflicts and form a standardized instruction set. Finally, according to the instruction format of the target device, protocol consistency encapsulation is completed, so that the instruction set fully matches the device's recognition requirements, resulting in a directly executable operation instruction set. This can ensure the semantic clarity, structural standardization, and device compatibility of the instructions, ensuring the effective execution of the operation instruction set and significantly improving the accuracy and efficiency of laboratory equipment control.

[0083] Reference Figure 2 The diagram shown is a flowchart illustrating a data processing-based laboratory equipment control method according to an embodiment of the present invention. In this embodiment, the data processing-based laboratory equipment control method includes:

[0084] S01. Perform multi-scale analysis on the raw data of the target device to obtain the multi-level stability characteristics of the target device; S02. Based on the multi-level stability characteristics, the dynamic operating state of the target device is subjected to topological structure evolution to obtain the state evolution manifold of the target device. S03. Based on the preset experimental procedure requirements, the correlation relationship of the state evolution manifold is mapped, and the fiber bundle structure of the mapping relationship is constrained and derived to obtain the continuous control section of the fiber bundle structure. S04. Eliminate outliers on the continuous control section to obtain the ideal control manifold of the continuous control section; S05. Perform folio segmentation on the ideal control manifold to obtain the basic folio structure of the ideal control manifold, and perform cross-sectional discretization on the basic folio structure to obtain the basic control action sequence of the basic folio structure. S06. Perform formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device.

[0085] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0086] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A laboratory equipment control system based on data processing, characterized in that, The system includes a multi-scale feature parsing module, a topological manifold evolution module, a fiber cross-section solving module, a singularity canonical resolution module, a foliate structure discretization module, and a semantic instruction encoding module, wherein: The multi-scale feature parsing module is used to perform multi-scale parsing on the raw data of the target device to obtain the multi-level stability features of the target device. The topology manifold evolution module is used to perform topology evolution on the dynamic operating state of the target device based on multi-level stability characteristics, so as to obtain the state evolution manifold of the target device. The fiber cross section solving module is used to map the correlation relationship of the state evolution manifold based on the preset experimental procedure requirements, and to derive the constraint of the fiber bundle structure of the mapping relationship to obtain the continuous control cross section of the fiber bundle structure. The singularity canonical resolution module is used to resolve outliers in a continuous control section to obtain the ideal control manifold of the continuous control section. The leaf structure discretization module is used to perform leaf structure segmentation on the ideal control manifold to obtain the basic leaf structure of the ideal control manifold, and to perform cross-sectional discretization on the basic leaf structure to obtain the basic control action sequence of the basic leaf structure. The semantic instruction encoding module is used to perform formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device.

2. The data processing-based laboratory equipment control system as described in claim 1, characterized in that, When performing multi-scale analysis on the raw data of the target device to obtain the multi-level stability features of the target device, the multi-scale feature parsing module is specifically used for: The original data of the target device is subjected to time-frequency joint decomposition to obtain a multi-scale representation of the original data; Cross-scale fusion of multi-scale representations yields the fused features of the target device. By structuring the fusion features, multi-level stability features of the target device are obtained.

3. The data processing-based laboratory equipment control system as described in claim 1, characterized in that, When the topology manifold evolution module performs topology evolution on the dynamic operating state of the target device based on multi-level stability characteristics to obtain the state evolution manifold of the target device, it is specifically used for: Based on multi-level stability characteristics, the dynamic operating state of the target device is embedded in a high-dimensional phase space to obtain the phase space point cloud of the dynamic operating state. Lifecycle tracking of multi-scale hole structures in phase space point clouds yields a dynamic persistent topological map. Based on the topological persistent graph, the phase space point cloud is reconstructed into a manifold to obtain a preliminary state surface of the dynamic running state. Based on the boundary conditions with multi-level stability characteristics, the boundary contraction of the state surface prototype is performed to obtain the state evolution manifold of the target device.

4. The data processing-based laboratory equipment control system as described in claim 3, characterized in that, When the topological manifold evolution module performs manifold reconstruction of the phase space point cloud based on the topological persistent graph to obtain a preliminary state surface of the dynamic running state, it is specifically used for: The key persistence intervals of the dimensional features of the topological persistent graph are quantized to obtain the key lifecycle parameter set of the topological persistent graph; Spatial statistics are fused from the phase space point cloud corresponding to the dimensional features to obtain the distribution correlation factor of the phase space point cloud; Based on the key lifecycle parameter set, the optimal reconstruction scale factor of the phase space point cloud is calculated; Based on the optimal reconstruction scale factor, the Riemannian degree is defined for the phase space point cloud to obtain the weighted phase space metric of the phase space point cloud; Based on weighted phase space metric, local spatial alignment and fusion of phase space point clouds are performed to obtain a preliminary state surface of dynamic operation.

5. The data processing-based laboratory equipment control system as described in claim 1, characterized in that, The fiber cross-section solving module, when executing preset experimental procedures, mapping the state evolution manifold to relationships, and deriving constraints on the mapped fiber bundle structure to obtain the continuous control cross-section of the fiber bundle structure, is specifically used for: The pre-set experimental procedure requirements are logically decomposed to obtain the set of process constraints required by the experimental procedure. Based on the state evolution manifold, the set of process constraints is filtered for compatibility to obtain a feasible subset of constraints for the state evolution manifold. Based on the state evolution manifold, the constraint space is projected onto the feasible constraint subset to obtain the fiber bundle structure of the state evolution manifold; Connectivity path screening is performed on fiber bundle structures to obtain a set of candidate through paths for fiber bundle structures; The set of candidate through paths is evaluated for its resistance to disturbance, and the compliant paths after evaluation are coordinated and integrated to obtain the continuous control section of the fiber bundle structure.

6. The data processing-based laboratory equipment control system as described in claim 5, characterized in that, The fiber cross-section solving module, when performing constraint space projection on a feasible subset based on the state evolution manifold to obtain the fiber bundle structure of the state evolution manifold, is specifically used for: Geometric discretization of the state evolution manifold yields a sample mesh of the state evolution manifold; Tangent bundle constraints are assigned to the sample point mesh to obtain the tangent space specification frame of the sample point mesh; Based on the tangent space standard frame, the feasible constraint subset is orthogonally decomposed to obtain the tangent projection vector and conormal component of the feasible constraint subset; Based on the tangential projection vector and the state evolution manifold, the overall coordination factor of the constraint projection is calculated; Based on the overall coordination factor, the fiber directivity of the tangential projection vector is tuned to obtain the standard fiber direction field of the tangential projection vector; By structurally closing the normed fiber orientation field and the conormal component, a fiber bundle structure of state evolution manifold is obtained.

7. The data processing-based laboratory equipment control system as described in claim 1, characterized in that, The singularity canonical resolution module, when performing anomaly resolution on a continuous control section to obtain the ideal control manifold of the continuous control section, is specifically used for: Local structural deformation is performed on the singularity neighborhood of the continuous control section to obtain the normalized coordinate expression of the singularity neighborhood; Based on the experimental procedure requirements, a constrained isomorphic mapping is applied to the normalized coordinate representation to obtain a corrected local representation of the singularity neighborhood. By geometrically merging the modified local representation with the continuous control section, an ideal control manifold with the continuous control section is obtained.

8. The data processing-based laboratory equipment control system as described in claim 1, characterized in that, The foliate discretization module, when performing foliate segmentation of the ideal control manifold to obtain the basic foliate structure of the ideal control manifold, and then performing cross-sectional discretization of the basic foliate structure to obtain the basic control action sequence of the basic foliate structure, is specifically used for: Actively perform simulated path extraction on the ideal control manifold to obtain the core motion path segment of the ideal control manifold; Based on the experimental procedure requirements, supplementary motion path planning is performed on the ideal control manifold to obtain auxiliary motion path segments of the ideal control manifold. By integrating the core action path segment and the auxiliary action path segment with temporal logic, the basic leaf structure of the ideal control manifold is obtained. The independent execution phases of the basic leaf-shaped structure are standardized and segmented to obtain the action primitives of the independent execution phases; Logically arrange the action primitives to obtain the basic control action sequence of the basic leaf structure.

9. The data processing-based laboratory equipment control system as described in claim 1, characterized in that, When the semantic instruction encoding module performs formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device, it is specifically used for: Context semantic binding is performed on the basic control action sequence to obtain the typed semantic sequence of the target device; By integrating the structural paradigms of the typified semantic sequences, an abstract syntax tree representation of the typified semantic sequences is obtained; Structural encoding is performed on the abstract syntax tree representation to obtain the standard instruction set of the abstract syntax tree representation; Based on the instruction format of the target device, the standard instruction set is encapsulated for protocol consistency to obtain the executable operation instruction set of the target device.

10. A laboratory equipment control method based on data processing, characterized in that, The method for using a data processing-based laboratory equipment control system as described in claim 1: S01. Perform multi-scale analysis on the raw data of the target device to obtain the multi-level stability characteristics of the target device; S02. Based on the multi-level stability characteristics, the dynamic operating state of the target device is subjected to topological structure evolution to obtain the state evolution manifold of the target device. S03. Based on the preset experimental procedure requirements, the correlation relationship of the state evolution manifold is mapped, and the fiber bundle structure of the mapping relationship is constrained and derived to obtain the continuous control section of the fiber bundle structure. S04. Eliminate outliers on the continuous control section to obtain the ideal control manifold of the continuous control section; S05. Perform folio segmentation on the ideal control manifold to obtain the basic folio structure of the ideal control manifold, and perform cross-sectional discretization on the basic folio structure to obtain the basic control action sequence of the basic folio structure. S06. Perform formal semantic encoding on the basic control action sequence to obtain the operation instruction set of the target device.

Images