Plant intelligent factory multi-dimensional data monitoring and collaborative management and control method and system

Abstract

The invention discloses a multi-dimensional data monitoring and collaborative management and control method and system for a plant intelligent factory, and belongs to the technical field of collaborative control, and the method specifically comprises the steps: collecting multi-dimensional data of the plant intelligent factory in real time, the multi-dimensional data comprising plant physiological parameters, environmental factor parameters, nutrient solution parameters and equipment and operation state parameters, and based on the multi-dimensional data, constructing a dynamic multi-level causal association model among equipment, plant physiology, environment and operation, identifying a potential cooperative influence path in an abnormal state, and automatically performing cross-level management and control when an abnormality is detected or a growth process is predicted to deviate from a trend. The cross-level management and control instructions are distributed to an equipment level, a cultivation unit level and a workshop level according to levels, and multi-link linkage regulation and control are carried out on the intelligent plant factory; according to the method, by establishing a causal association and path cooperation mechanism, regulation and control are more accurate, flexible and adaptive, and the stability, resource utilization rate and intelligent level of plant production are effectively improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of collaborative control, and in particular to a plant intelligent factory multi-dimensional data monitoring and collaborative control method and system. BACKGROUND

[0002] With the deep integration of modern agriculture and intelligent manufacturing technology, plant factories have gradually become an important mode to realize efficient agricultural production. Plant factories realize controllability and standardization of the whole process of plant growth through artificial light sources, climate regulation, nutrient supply and intelligent monitoring. However, existing plant factories mostly rely on single-dimensional monitoring methods, such as environmental temperature and humidity monitoring or nutrient solution concentration monitoring, which cannot comprehensively integrate multi-dimensional information such as plant physiological state, environmental factors, equipment operation and management personnel operation, so it is difficult to realize stable and efficient production control under complex dynamic conditions.

[0003] At present, some plant factories have introduced Internet of Things, big data and automatic control systems, which have realized data collection and centralized management to a certain extent. However, most of these systems use static thresholds and empirical rules for judgment, and lack cross-level data fusion and causal correlation modeling. For example, when plants show abnormal growth, it is difficult to analyze the linkage between lighting, carbon dioxide concentration, nutrient solution supply and equipment operation state at the same time, resulting in inaccurate abnormal positioning, lagging control strategy, and even possible resource waste and production risk.

[0004] In addition, most of the existing control methods focus on single-link optimization and lack multi-level collaborative mechanisms. In a complex plant factory production chain, plant physiological response, environmental disturbance, equipment maintenance and manual operation are coupled with each other, and single-link adjustment is difficult to cope with production deviation under multi-factor linkage. SUMMARY

[0005] In view of the deficiencies of the prior art, the plant intelligent factory multi-dimensional data monitoring and collaborative control method and system are proposed, which can perform dynamic causal modeling based on multi-dimensional data, combine cross-level collaborative control, and have a method with continuous optimization and evolution capability, thereby comprehensively improving the stability, flexibility and intelligent level of the plant factory.

[0006] To achieve the above purpose, the application provides the following technical scheme:

[0007] The plant intelligent factory multi-dimensional data monitoring and collaborative control method comprises:

[0008] Real-time collection of multi-dimensional data of the plant intelligent factory, the multi-dimensional data comprising plant physiological parameters, environmental factor parameters, nutrient solution parameters, and equipment and operation state parameters;

[0009] Based on the multi-dimensional data, a dynamic multi-level causal correlation model between equipment, plant physiology, environment and operation is constructed, and a potential synergistic influence path in an abnormal state is identified.

[0010] When an anomaly is detected or a growth process is predicted to deviate from a trend, automatic cross-level management is performed, cross-level management instructions are distributed to the equipment level, the cultivation unit level and the workshop level according to the level, and multi-link joint regulation and control of the plant intelligent factory is performed.

[0011] Specifically, based on the multi-dimensional data, a dynamic multi-level causal correlation model between equipment, plant physiology, environment and operation is constructed, and a potential synergistic influence path in an abnormal state is identified, including:

[0012] The multi-dimensional data is hierarchically preprocessed according to the equipment parameter layer, the plant physiology layer, the environmental factor layer and the operation layer, and the data in the same layer is normalized and time-synchronized.

[0013] By establishing a multi-level feature index, key factors with potential coupling relationships between layers are identified, and a cross-layer correlation factor set is generated.

[0014] According to the cross-layer correlation factor set, a time sequence interaction sequence between factors of different levels is constructed, and the time sequence interaction sequence represents the factor sequence and transmission path in the dynamic change process.

[0015] Based on the time sequence interaction sequence, the key factors of the equipment parameter layer, the plant physiology layer, the environmental factor layer and the operation layer are mapped to a multi-level causal graph, and cross-layer action links are marked in the graph.

[0016] In the multi-level causal graph, according to a preset path traversal logic, a potential synergistic influence path corresponding to an abnormal state is extracted.

[0017] Specifically, based on the time sequence interaction sequence, the key factors of the equipment parameter layer, the plant physiology layer, the environmental factor layer and the operation layer are mapped to a multi-level causal graph, and cross-layer action links are marked in the graph, including:

[0018] The equipment factors, plant physiology factors, environmental factors and operation factors in the time sequence interaction sequence are abstracted into graph nodes, and each node is assigned a unique identifier.

[0019] According to the time sequence dependency relationship between factors of the same level, intra-layer causal links are generated in the causal graph, and the intra-layer causal links reflect the dynamic interaction logic between key factors of the same layer.

[0020] The factor pairs with cross-layer time sequence dependency relationships are traversed, and cross-layer action links are established in the causal graph to mark the causal connections between different levels.

[0021] The intra-layer causal link is structurally integrated with the cross-layer action link to form a multi-level causal graph with hierarchical topological characteristics.

[0022] Specifically, in the multi-level causal graph, according to a preset path traversal logic, a potential synergistic influence path corresponding to an abnormal state is extracted, including:

[0023] In the multi-level causal graph, according to trigger information corresponding to the abnormal state, a node related to the abnormality is determined as a traversal starting anchor point;

[0024] Starting from the traversal starting anchor point, according to a preset path traversal logic, recursively visit the successor nodes that have causal relationship with the traversal starting anchor point, and form a candidate path set;

[0025] The candidate path set is subjected to causal consistency test one by one, and the paths that do not conform to the graph logic or are irrelevant to the abnormal state are excluded, and an effective path that meets the constraint condition is generated;

[0026] The effective path is structurally collected to generate a potential synergistic influence path corresponding to the abnormal state.

[0027] Specifically, when detecting an abnormality or predicting that the growth process deviates from the trend, cross-level management is automatically performed, and cross-level management instructions are distributed to the device level, the cultivation unit level and the workshop level according to the level, and the plant intelligent factory is multi-link joint regulation and control, including:

[0028] The multi-source trigger information generated by abnormality detection or growth process prediction is merged and processed to generate a cross-level management event, and the scope, time limit and priority label of the cross-level management event are labeled;

[0029] Based on the potential synergistic influence path, a controlled object set and an inhibition boundary are determined to form a control intention containing target state constraints, resource constraints and time sequence constraints;

[0030] According to the control intention, the control action is decomposed into an atomic instruction sequence of the device level, the cultivation unit level and the workshop level, the upstream and downstream dependency relationship and the execution window are established, and a complete instruction for cross-layer scheduling call is generated;

[0031] The atomic instruction sequence is subjected to resource occupation, time sequence and safety mutual exclusion test, when mutual exclusion is detected, priority arbitration and alternative sequence reconstruction are performed to generate an executable list that meets the constraint condition;

[0032] The executable list is issued to the corresponding execution end according to the level, and the plant intelligent factory is multi-link joint regulation and control.

[0033] Specifically, the controlled object set and the forbidden boundary are determined based on the potential synergistic influence path to form a management and control intention containing target state constraints, resource constraints and timing constraints, including:

[0034] In the potential synergistic influence path, the controlled object set to be implemented is determined according to the node causal relationship, and an independent index is established for each controlled object;

[0035] For the controlled object set, a forbidden boundary is set to limit the operation range that cannot be triggered according to the conflict conditions existing in the cross-layer action link;

[0036] The controlled object set and the forbidden boundary are combined to generate a management and control constraint set containing target state constraints, resource constraints and timing constraints;

[0037] The management and control constraint set is structured and integrated to form a complete management and control intention.

[0038] Specifically, according to the management and control intention, the management and control action is decomposed into atomic instruction sequences at the device level, the cultivation unit level and the workshop level, the upstream and downstream dependency relationship and the execution window are established, and the complete instruction for cross-layer scheduling call is generated, including:

[0039] The management and control intention is parsed into atomic instruction sequences at the device level, the cultivation unit level and the workshop level, and each instruction is assigned a unique identifier;

[0040] According to the trigger sequence and resource occupation condition in the atomic instruction sequence, an upstream and downstream dependency relationship chain is established;

[0041] Combined with the dependency relationship chain, the corresponding execution window is divided according to the time interval and parallelism constraint, and each instruction is mapped to the corresponding execution window;

[0042] The mapped atomic instruction and its dependency relationship and execution window are serialized and collected to generate a complete instruction for cross-layer scheduling call.

[0043] Specifically, the atomic instruction sequence is subjected to resource occupation, timing sequence and safety mutual exclusion inspection, when mutual exclusion is detected, priority arbitration and replacement sequence reconstruction are performed to generate an executable list that meets the constraint conditions, including:

[0044] The atomic instruction sequence is subjected to resource occupation checking, timing sequence checking and safety mutual exclusion checking to generate an inspection result set containing conflict markers and trigger conditions;

[0045] The inspection result set is mapped to the instruction dependency relationship chain to locate the instruction nodes and their upstream and downstream associated nodes that have conflicts, and to divide the non-parallel domain and the rearrangeable domain accordingly;

[0046] In the non-parallel domain, according to the control intention, the forbidden boundary and the execution window, the priority arbitration is performed on the related instructions to determine a reserved instruction, a delayed instruction and a replacement instruction.

[0047] Under the constraint of the rearrangement domain and the replacement instruction set, the instruction sequence satisfying the dependency relationship and the execution window is reconstructed, and an executable list containing the instruction sequence, the execution window and the mutual exclusion shielding rule is output.

[0048] The plant intelligent factory multi-dimensional data monitoring and collaborative control system is used for realizing the plant intelligent factory multi-dimensional data monitoring and collaborative control method, and comprises a data acquisition module, an influence path identification module and a linkage control module.

[0049] The data acquisition module is used for acquiring the multi-dimensional data of the plant intelligent factory in real time, and the multi-dimensional data comprises plant physiological parameters, environmental factor parameters, nutrient solution parameters and equipment and operation state parameters.

[0050] The influence path identification module constructs a dynamic multi-level causal correlation model among equipment, plant physiology, environment and operation based on the multi-dimensional data, and identifies a potential collaborative influence path in an abnormal state.

[0051] The linkage control module is used for automatically performing cross-level control when an abnormality is detected or a growth process deviating trend is predicted, distributing cross-level control instructions to the equipment level, the cultivation unit level and the workshop level according to the level, and performing multi-linkage linkage control on the plant intelligent factory.

[0052] Specifically, the linkage control module comprises an intention identification unit, an instruction generation unit and a linkage control unit.

[0053] The intention identification unit determines a controlled object set and a forbidden boundary based on the potential collaborative influence path, and forms a control intention containing a target state constraint, a resource constraint and a timing constraint.

[0054] The instruction generation unit is used for decomposing control actions into atomic instruction sequences of the equipment level, the cultivation unit level and the workshop level according to the control intention, and generating complete instructions for cross-level scheduling calls.

[0055] The linkage control unit is used for distributing executable lists to corresponding execution ends according to the level, and performing multi-linkage linkage control on the plant intelligent factory.

[0056] Compared with the prior art, the plant intelligent factory multi-dimensional data monitoring and collaborative control system has the following beneficial effects:

[0057] The present application proposes a plant intelligent factory multi-dimensional data monitoring and collaborative control method and system, which integrates plant physiological parameters, environmental factors, nutrient solution parameters and equipment and operation states into a unified data framework, and builds a dynamic correlation relationship across layers based on causal modeling. When an abnormal state or growth process deviation trend occurs, the potential collaborative influence path can be quickly identified, and cross-layer control intentions and executable lists can be generated, realizing multi-linkage linkage regulation and control from the device level, cultivation unit level to workshop level. The overall method not only realizes global perception and dynamic control of complex elements of the plant factory, but also through the establishment of a collaborative mechanism of causal correlation and path, makes the regulation and control more accurate, flexible and adaptive, thereby effectively improving the stability, resource utilization rate and intelligent level of plant production. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 A plant intelligent factory multi-dimensional data monitoring and collaborative control method flowchart is provided for the present application.

[0059] Figure 2 A principle structure diagram of a multi-level causal correlation model is provided for the present application.

[0060] Figure 3 A linkage regulation and control flowchart is provided for the present application.

[0061] Figure 4 A plant intelligent factory multi-dimensional data monitoring and collaborative control system architecture diagram is provided for the present application. DETAILED DESCRIPTION

[0062] The present application will be described in detail below with specific embodiments. The following examples will help those skilled in the art to further understand the present application, but do not limit the present application in any form. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made. These all belong to the protection scope of the present application.

[0063] In order to make the purpose, technical scheme and advantages of the present application more clear and obvious, the present application will be further described in detail below in combination with the drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0064] It should be noted that the various features of the embodiments of the present application can be combined with each other, and all within the protection scope of the present application, if there is no conflict. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. In addition, the "first", "second", "third" and the like used in the present application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same function and effect.

[0065] Unless otherwise defined, all technical and scientific terms used in the present application have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the present application are only for the purpose of describing the specific embodiments of the present application, and are not used to limit the present application. The term "and / or" used in the present application includes any and all combinations of one or more related listed items.

[0066] Embodiment 1

[0067] Please refer to Figures 1-3 The present application provides a plant intelligent factory multi-dimensional data monitoring and collaborative control method, comprising the following specific steps:

[0068] Step S1: Real-time acquisition of multi-dimensional data of the plant intelligent factory, the multi-dimensional data comprising plant physiological parameters, environmental factor parameters, nutrient solution parameters, and equipment and operation state parameters.

[0069] In the present embodiment, multi-source sensors and monitoring nodes need to be deployed inside the plant intelligent factory to obtain plant physiological parameters, environmental factor parameters, nutrient solution parameters, and equipment and operation state parameters; plant physiological parameters reflect the plant growth state through indicators such as chlorophyll fluorescence, leaf temperature or transpiration intensity; environmental factor parameters describe the effect of the external environment on the plant through data such as light, air temperature and humidity, and carbon dioxide concentration; nutrient solution parameters depict root absorption of the environment through information such as pH, conductivity and nutrient concentration; and equipment and operation state parameters are composed of lighting parameters, irrigation parameters, climate control equipment parameters, and manual operation record parameters.

[0070] Step S2: Based on the multi-dimensional data, a dynamic multi-level causal correlation model between equipment, plant physiology, environment and operation is constructed to identify potential collaborative influence paths in abnormal states.

[0071] The specific steps of step S2 are:

[0072] Step S201: The multi-dimensional data is hierarchically preprocessed according to the device parameter layer, the plant physiological layer, the environmental factor layer and the operation layer, and the data in the same layer is normalized and time-synchronized.

[0073] In the embodiment, the collected multi-dimensional data is divided into the device parameter layer, the plant physiological layer, the environmental factor layer and the operation layer according to the data source and the physical property, so as to ensure that the data of different categories has clear hierarchical boundaries when modeling; then, in each layer, the numerical data needs to be normalized to solve the problem of inconsistent dimensions and sampling frequencies, so that the data has comparability in the same numerical interval and avoids weight deviation caused by scale difference; at the same time, considering the situation that the time stamps of different collection nodes are not aligned, time synchronization is realized by interpolation, resampling or time window alignment, so that the data points in the same layer can be corresponded to a unified time sequence reference. Through the hierarchical preprocessing principle, four hierarchical normalized data sets are finally obtained.

[0074] Step S202: A multi-level feature index is established to identify key factors with potential coupling relationship between layers and generate a cross-layer associated factor set.

[0075] In the embodiment, after the hierarchical preprocessing is completed, a multi-level feature index is established for the data of the device parameter layer, the plant physiological layer, the environmental factor layer and the operation layer. The index realizes the localization and correlation of cross-layer data by defining the semantic label, time sequence identifier and functional attribute of each type of factor. Specifically, by comparing the response mode and change trend of data in different layers on the time sequence, key factors with mutual coupling characteristics are identified, such as the linkage relationship between plant leaf photosynthetic rate and light intensity, the synchronous change between nutrient solution conductivity and root transpiration rate, etc. It should be noted that the identification process not only considers the direct correlation between factors, but also combines the upstream and downstream logical relationship to extract factor combinations with indirect action links. Through the process, a set of cross-layer associated factor set is finally formed, which can represent the potential coupling relationship between multi-layer data.

[0076] Step S203: According to the cross-layer associated factor set, a time sequence interaction sequence between factors of different levels is constructed, which represents the factor sequence and transmission path in the dynamic change process.

[0077] In this embodiment, after obtaining the cross-layer association factor set, the factors need to be logically arranged in chronological order to generate a time sequence interaction sequence that can reflect the causal progression relationship; specifically, by aligning and comparing the change trend of different levels of factors on the time axis, the triggering relationship between the change of the first occurring factor and the subsequent response factor is identified, and this front and back connection relationship is recorded in a serialized manner; it should be noted that the construction of the time sequence interaction is not limited to a single direct cause and effect, but should cover multiple transmission paths across levels, for example, the change of light intensity in the environmental factor layer first causes the fluctuation of transpiration rate in the plant physiology layer, and further affects the circulation flow in the nutrient solution layer. Through this layer-by-layer progressive way, a set of dynamic interaction sequences is finally obtained.

[0078] Step S204: Based on the time sequence interaction sequence, map the device parameter layer, plant physiology layer, environmental factor layer and operation layer key factors to the multi-level causal graph, and mark the cross-layer action link in the graph.

[0079] The specific steps of step S204 are:

[0080] Step S2041: Abstract the device factors, plant physiology factors, environmental factors and operation factors in the time sequence interaction sequence into graph nodes respectively, and assign a unique identifier to each node.

[0081] In this embodiment, in order to realize unified representation across levels in the causal graph, each type of factor in the time sequence interaction sequence needs to be abstracted first; specifically, device factors such as lighting power and irrigation pump rate, plant physiology factors such as photosynthetic rate and leaf temperature, environmental factors such as air humidity and carbon dioxide concentration, and operation factors such as manual fertilization and maintenance operation, are all abstracted into independent nodes in the graph; in order to ensure the uniqueness of subsequent retrieval and calling, each node needs to be assigned a unique identifier, which contains information such as factor category, time stamp and attribute label, to ensure that factors of the same type can be accurately distinguished at different times or in different operation scenarios; through this abstraction and identification operation, the time sequence interaction sequence is transformed from the original multi-dimensional data stream to a structured node set.

[0082] Step S2042: According to the time sequence dependency relationship between factors in the same level, generate intra-layer causal links in the causal graph, which reflect the dynamic interaction logic between key factors in the same layer.

[0083] In the embodiment, in the construction process of the causal graph, it is necessary to establish intra-layer causal links for factors in the same layer according to their dependency in time series; specifically, by analyzing the change pattern of factors in the same layer on the time axis, the logical relationship between the pre-trigger and the subsequent response is identified, for example, in the plant physiology layer, the increase of photosynthetic rate usually precedes the change of transpiration intensity, and in the device layer, the start of the irrigation pump usually precedes the increase of the nutrient solution flow; it should be noted that the dependency relationship is not a simple numerical correlation, but a dynamic interaction structure extracted based on the functional logic and time sequence rule between factors; by mapping these dependency relationships into directional links in the graph, a network representing the dynamic logic of factors can be formed within the layer.

[0084] Step S2043: traversing the factor pairs with cross-layer time sequence dependency relationship, and establishing cross-layer action links in the causal graph to mark the causal connection between different layers.

[0085] In the embodiment, after generating the intra-layer causal links, it is necessary to further identify the time sequence dependency relationship between the cross-layer factors, and establish cross-layer action links in the causal graph; specifically, by traversing the factor pairs of the device layer, the plant physiology layer, the environment layer and the operation layer one by one, the change rule of the time sequence is compared, if it is found that the fluctuation of a factor in a layer continuously leads the response of a factor in another layer, it is determined that there is a cross-layer dependency relationship between them; for example, the change of light intensity in the environment layer may precede the chlorophyll fluorescence response in the plant physiology layer, and the fertilization action in the operation layer may precede the change of conductivity in the nutrient solution layer; it should be noted that when establishing the cross-layer action link, the inter-layer logical constraint should be combined to ensure that the link not only reflects the time sequence relationship, but also embodies the rationality of causal driving; finally, the identified factor pairs are mapped into the cross-layer connection with direction in the graph, thereby forming a causal topological framework covering different layers.

[0086] Step S2044: structurally integrating the intra-layer causal links and the cross-layer action links to form a multi-layer causal graph with hierarchical topological characteristics.

[0087] In this embodiment, after the construction of intra-layer causal links and cross-layer action links is completed, the two are needed to be structured and integrated to form a multi-level causal graph with hierarchical topology characteristics; specifically, first, the causal links within the same layer are taken as local subgraphs to maintain the internal logical relationship of each layer factor; then the cross-layer action links are introduced and matched with the nodes of the corresponding subgraph, so that the cross-layer dependence can connect different subgraphs as a whole network through the bridge; it should be noted that the node identification, time sequence and logical constraints should be unified during the integration process to avoid repeated mapping or logical conflicts; through the structured integration operation, a causal graph composed of multi-level subgraphs and cross-layer connections is finally obtained.

[0088] Step S205: In the multi-level causal graph, according to the preset path traversal logic, extract the potential synergistic influence path corresponding to the abnormal state.

[0089] The specific steps of step S205 are:

[0090] Step S2051: In the multi-level causal graph, determine the node related to the abnormality as the traversal starting anchor point according to the trigger information corresponding to the abnormal state.

[0091] In this embodiment, on the premise that the multi-level causal graph has been established, the starting anchor point of traversal needs to be located according to the trigger information corresponding to the abnormal state; specifically, first, the characteristics of the abnormal state are analyzed, and the factor categories, occurrence time and associated level information involved are extracted; then these information is matched with the node identification in the causal graph, so as to screen out the target node directly related to the abnormality; for example, when the photosynthetic rate of the plant physiological layer is monitored to be abnormally decreased, the node is marked as an abnormal anchor point; if the light intensity of the environment layer is detected to be suddenly changed, the node is taken as an anchor point candidate; it should be noted that when determining the anchor point, the trigger position of the factor in the causal graph and its possible downstream influence range are given priority, so as to ensure that the subsequent path traversal can be expanded along the causal chain related to the abnormality; through this process, the traversal starting anchor point corresponding to the abnormal state is finally obtained.

[0092] Step S2052: Starting from the traversal starting anchor point, recursively visit the successor nodes that have causal relationship with the traversal starting anchor point according to the preset path traversal logic, and form a candidate path set.

[0093] In this embodiment, after determining the traversal starting anchor point, it is necessary to recursively propagate from the anchor point layer by layer according to the preset path traversal logic to identify the successor nodes having a causal relationship with the anchor point. Specifically, first, according to the directionality of the links in the causal graph, the nodes are expanded in the downstream order of time or logical trigger; at each recursive step, it is necessary to determine whether the node satisfies the cross-layer or intra-layer dependency constraint, and if it satisfies, it is included in the traversal path and the expansion continues; through continuous iterative expansion, candidate path branches connected by multiple nodes are gradually formed; it should be noted that the formation of the candidate path not only considers the directly connected successor nodes, but also covers the paths that may have multiple indirect connections, so as to ensure that the abnormal state related causal propagation chain is captured completely; finally, the candidate path set generated by the traversal logic is obtained.

[0094] Step S2053: The causal consistency of the candidate path set is verified one by one, and the paths that do not conform to the graph logic or are irrelevant to the abnormal state are excluded to generate valid paths that meet the constraint conditions.

[0095] In this embodiment, after obtaining the candidate path set, it is necessary to verify the causal consistency of each path to ensure its logical rationality and relevance to the abnormal state. Specifically, first, the causal links between adjacent nodes in the path are compared one by one to verify whether their directionality is consistent with the existing topological rules in the causal graph, and if there is a reverse or broken case, it is excluded. Secondly, the node states in the path are matched with the abnormal trigger information to determine whether the path truly reflects the causal chain of abnormal propagation, and if it is found that the node change has no direct or indirect association with the abnormal state, the path is considered invalid. Finally, according to the preset constraint conditions such as time window consistency and cross-layer logical constraint, the path as a whole is comprehensively evaluated to select the path that meets the conditions. Through this process, a set of valid paths is finally obtained, which can accurately represent the transmission logic of the abnormal state among multiple layers of factors.

[0096] Step S2054: The valid paths are structured and collected to generate potential synergistic influence paths corresponding to the abnormal state.

[0097] In this embodiment, after obtaining the effective paths meeting the causal consistency test, the paths are structured and collected to form potential synergistic influence paths that can directly correspond to abnormal states. Specifically, first, the effective paths are reordered and grouped according to the hierarchical attributes and time sequence of the nodes in the paths, to ensure that the causal relationship of different hierarchical factors is clearly presented. Then, through a unified path coding method, the nodes, links and constraint conditions involved are encapsulated into standardized path units, thereby realizing the indexability and reusability of the paths. In this process, the intersection between different effective paths needs to be merged to avoid repeated expression or logical conflicts. It should be noted that this collection operation not only preserves the independence of each path, but also forms a more comprehensive synergistic influence set through integration, ultimately generating potential synergistic influence paths.

[0098] Figure 2 The principle structure diagram of the multi-level causal correlation model is shown. The structure diagram takes the device parameter layer, the plant physiology layer, the environmental factor layer and the operation layer as basic units, and represents the action relationship between factors through nodes and links. Each layer internally contains several same-layer factors, and the dynamic logical relationship between them is described by intra-layer causal links. Different levels are connected through cross-layer action links. The dashed line between the same-layer factors represents the time sequence dependence or logical correlation relationship between the key factors within the same level. For example, in the device parameter layer, there is a dependent logic between the irrigation pump start-stop signal and the nutrient solution flow data. In the plant physiology layer, there is also a dynamic coupling between the photosynthetic rate change and the transpiration intensity change. The dashed line with an arrow represents the causal action path between cross-levels, and the arrow direction represents the trigger order or causal transmission direction between factors. For example, the change of light intensity in the environmental factor layer can precede the change of leaf photosynthetic rate in the plant physiology layer, so that the dashed line with an arrow is marked in the causal graph, indicating that the action points from the environmental factor layer to the plant physiology layer.

[0099] Specifically, the present application constructs a causal network with hierarchical topological characteristics. When an abnormal state occurs, the causal path marked in the graph can be traversed to quickly identify the potential synergistic influence path related to the abnormality.

[0100] Step S3: When an abnormality is detected or a growth process is predicted to deviate from the trend, cross-level control is automatically performed, and cross-level control instructions are distributed to the device level, the cultivation unit level and the workshop level according to the level, to carry out multi-link joint regulation and control of the plant intelligent factory.

[0101] As shown in Figure 3 , the specific steps of step S3 are:

[0102] Step S301: Merge the multi-source trigger information generated by the anomaly detection or growth process prediction, generate a cross-level management event, and label the scope, time limit and priority label of the cross-level management event.

[0103] In this embodiment, during the operation of the plant intelligent factory, the anomaly detection module and the growth process deviation prediction module will continuously output trigger information of different sources, which may come from plant physiological monitoring, environmental factor fluctuation, nutrient solution supply anomaly and equipment operation deviation. In order to avoid redundancy or conflict caused by information fragmentation, it is necessary to merge these multi-source trigger information. Specifically, first, the trigger events in the same time window are aggregated to identify whether they point to the same abnormal category or have overlapping relationship on the causal link. Then, the aggregated events are abstracted into a unified cross-level management event, and key metadata are attached in its structure, including event scope, such as affected level range and object set, time limit, such as constraint that must be processed within a certain period, and priority label, such as sorting according to the severity of the anomaly or the risk to yield and quality. Through the merging and labeling process, a cross-level management event with unified semantics and operation attributes is formed.

[0104] Step S302: Based on the potential synergistic influence path, determine the controlled object set and the prohibited boundary, and form a management intention containing target state constraint, resource constraint and time sequence constraint.

[0105] The specific steps of step S302 are:

[0106] Step S3021: In the potential synergistic influence path, determine the controlled object set that needs to be managed according to the node causal relationship, and establish an independent index for each controlled object.

[0107] In this embodiment, after the potential synergistic influence path has been extracted, it is necessary to further identify the object set that actually needs to be managed in the path. Specifically, first, traverse the nodes in the path, analyze their position and action strength in the abnormal propagation combining the directionality of the causal link, and filter out the nodes that are in the key driving link or have a decisive effect on the abnormal diffusion, such as the leaf photosynthetic efficiency node in the plant physiological layer, the carbon dioxide concentration node in the environment layer, the conductivity node in the nutrient solution layer or the irrigation pump start-stop node in the equipment layer. Then, an independent index is established for each controlled object, which is composed of object category, belonging level, time stamp and location identifier and other information, to ensure that different objects can be accurately located and scheduled in the same scene. Through this identification and indexing process, a controlled object set with clear boundaries and operable attributes is finally obtained.

[0108] Step S3022: For the set of controlled objects, set the forbidden boundary to limit the operation range that cannot be triggered according to the conflict conditions existing in the cross-layer action link.

[0109] In this embodiment, after determining the set of controlled objects, the forbidden boundary is set for these objects in combination with the potential conflict conditions in the cross-layer action link to limit their operation range; specifically, first, the cross-layer link is traversed to analyze whether there are resource occupation conflicts, timing dependency contradictions or logic exclusion situations in the execution process of different levels of factors, for example, the high-frequency start-stop of the irrigation pump may conflict with the stability of the nutrient solution circulation, and the light intensity enhancement operation may be mutually restricted with the start of the cooling fan at a specific time period; then, these conflict conditions are mapped to the set of controlled objects, the operation boundary that cannot be triggered is marked for the related objects, and it is solidified in the form of restriction rules in the management and control framework; it should be noted that the forbidden boundary not only covers the hard prohibition conditions, but also includes the restrictions that dynamically take effect in a specific environmental context, ensuring that new contradictions or risks are not introduced when executing the control actions; in this way, a set of forbidden boundaries corresponding to the set of controlled objects is finally formed.

[0110] Step S3023: In combination with the set of controlled objects and the forbidden boundary, a management and control constraint set containing target state constraints, resource constraints and timing constraints is generated.

[0111] In this embodiment, after obtaining the set of controlled objects and their corresponding forbidden boundaries, a unified management and control constraint set is further constructed to ensure that the subsequent instructions meet the multi-dimensional condition restrictions; specifically, first, for each controlled object, the target state constraint is set in combination with the expected value of the target state and the abnormal correction demand to limit the final regulation direction of the object; second, according to the resource consumption relationship of each controlled object in the cross-layer causal chain, the resource constraint condition is defined, for example, the nutrient solution supply amount should not exceed the maximum flow of the circulation system, and the lighting power should not exceed the upper limit of the power distribution; third, in combination with the logical dependency relationship and the time sequence between objects, the timing constraint is generated to regulate the sequence and parallelism of instruction execution; it should be noted that the management and control constraint set is organized in a structured manner, which can cover the requirements of target orientation, resource allocation and time sequence.

[0112] Step S3024: The management and control constraint set is structured and integrated to form a complete management and control intention.

[0113] In this embodiment, after the target state constraints, resource constraints and timing constraints are generated respectively, they need to be structured and integrated to form a complete management intention that can directly drive the generation of subsequent instructions; Specifically, first, map the three types of constraint conditions according to the index of the controlled object, so that each object corresponds to a complete set of constraint rules; Then, through the logical rule engine, the constraints between different objects are merged, and the priority coverage or condition conflict existing therein is processed, so that the overall constraint system remains consistent in the global range; Then, the integrated results are structured and packaged to form an intention unit containing constraint levels, action ranges and trigger conditions; Finally, the intention unit is associated with the cross-level management event to realize the traceable logical chain from the abnormal state to the management action.

[0114] Step S303: According to the management intention, the management action is decomposed into atomic instruction sequences at the device level, the cultivation unit level and the workshop level, the upstream and downstream dependency relationship and the execution window are established, and complete instructions for cross-layer scheduling are generated.

[0115] The specific steps of step S303 are:

[0116] Step S3031: The management intention is parsed into atomic instruction sequences at the device level, the cultivation unit level and the workshop level, and each instruction is assigned a unique identifier.

[0117] In this embodiment, after the complete management intention is formed, it is translated into executable atomic instruction sequences and is decomposed by level; Specifically, first, according to the target state, resource allocation and timing constraints defined in the management intention, the overall management requirement is decomposed into the smallest granularity control action, for example, the device-level instruction corresponds to the start and stop of the irrigation pump or the lighting adjustment, the cultivation unit-level instruction corresponds to the nutrient solution supply or air circulation control of a specific crop area, and the workshop-level instruction corresponds to the overall environmental regulation or energy consumption allocation; Then, each atomic instruction is assigned a unique identifier, which is composed of level attributes, object index, action type and timestamp; It should be noted that the instruction parsing process not only guarantees the logical integrity of the management intention, but also converts complex multi-level regulation requirements into schedulable and traceable instruction units.

[0118] Step S3032: According to the trigger sequence and resource occupation condition in the atomic instruction sequence, the upstream and downstream dependency relationship chain is established.

[0119] In the embodiment, after the sequence of atomic instructions is generated and assigned with unique identifiers, further upstream and downstream dependency chains are established according to the execution logic thereof; specifically, first, the trigger sequence of each instruction is analyzed, if the execution result of a certain instruction constitutes the prerequisite condition of a subsequent instruction, a sequential dependency relationship is established therebetween, for example, the irrigation valve opening instruction must precede the nutrient solution flow regulation instruction; second, the conflict of instructions in resource occupation is tested, when multiple instructions involve the same resource unit and cannot be executed in parallel, the execution sequence thereof needs to be constrained through the dependency chain, for example, the lighting power distribution and ventilation power regulation need to avoid simultaneous request overload in the same time period; it should be noted that the dependency chain not only includes direct sequential connection, but also covers the logical interlocking between cross-layer instructions, thereby organizing the scattered sequence of atomic instructions into an ordered chain structure; through this process, the upstream and downstream dependency chains reflecting the execution logic and resource constraints are finally obtained.

[0120] Step S3033: in combination with the dependency chain, the corresponding execution window is divided according to the time interval and parallelism constraint, and each instruction is mapped to the corresponding execution window.

[0121] In the embodiment, after the upstream and downstream dependency chains are established, the execution process of the atomic instructions is mapped to a specific time framework, ensuring that the control actions are implemented in order under the conditions of logical correctness and resource availability; specifically, first, the earliest executable time and the latest allowable completion time of each instruction are determined according to the preceding and following constraints in the dependency chain, and the initial time interval is divided based thereon; then, according to the parallelism constraint, instructions that can be executed simultaneously and do not conflict with each other are grouped, so that they are mapped to the same execution window, while instructions that exist conflict or dependency relationship are allocated to adjacent or delayed execution windows; in this process, the scheduling of cross-layer instructions is corrected to ensure that the actions of different levels remain consistent in the time dimension; it should be noted that the finally generated execution window not only determines the execution interval of the instructions, but also provides operational boundary conditions for the parallel and serial relationship between instructions, forming a structured time scheduling framework.

[0122] Step S3034: the mapped atomic instructions and their dependency relationships and execution windows are serialized and collected to generate complete instructions for cross-layer scheduling calls.

[0123] In this embodiment, after the atomic instructions are mapped to the execution window, the instructions and their corresponding dependency relationship and execution window information are unified and serialized to form complete instructions that can be called by cross-layer scheduling. Specifically, first, the unique identifier of each instruction is bound to its execution window and upstream and downstream dependency nodes to ensure that the instruction can be correctly parsed when called. Then, all the bound instructions are concatenated in time sequence and logical order to form a structured serialized collection. In this process, concurrent conflicts and timing contradictions between cross-layer instructions also need to be adjusted to make the final sequence meet the constraints of the dependency relationship chain and the scheduling requirements of the execution window. It should be noted that this serialization collection operation not only converts scattered atomic instructions into a complete instruction set.

[0124] Step S304: Resource occupation, timing sequence and safety mutual exclusion verification are performed on the atomic instruction sequence. When mutual exclusion is detected, priority arbitration and replacement sequence reconstruction are performed to generate an executable list that meets the constraint conditions.

[0125] The specific steps of step S304 are:

[0126] Step S3041: Resource occupation checking, timing sequence checking and safety mutual exclusion checking are performed on the atomic instruction sequence to generate a verification result set containing conflict markers and trigger conditions.

[0127] In this embodiment, after the serialized atomic instruction collection is generated, it is checked to ensure that execution exceptions will not occur due to resource conflicts or logical contradictions in the subsequent scheduling process. Specifically, first, in the resource occupation checking, instructions involving the same resource unit are compared to determine whether there is resource overlap or exceeding the threshold, such as the same irrigation pipeline being occupied by different instructions at the same time. Second, in the timing sequence checking, the execution order of the instructions is checked according to the dependency relationship chain. If reverse order calling or execution without satisfying the precondition is found, it is marked as a timing conflict. Third, in the safety mutual exclusion checking, instruction combinations that may cause danger or violate operating constraints are detected, such as the simultaneous occurrence of lighting power increase and cooling fan shutdown. Through the above multi-dimensional checking, a verification result set is finally generated, which contains the markers and trigger conditions of various conflicts.

[0128] Step S3042: Map the verification result set to the instruction dependency relationship chain, locate the conflicting instruction nodes and their upstream and downstream associated nodes, and divide the non-parallel domain and the rearrangeable domain accordingly.

[0129] In this embodiment, after obtaining the test result set containing the conflict label and the trigger condition, it is mapped to the existing instruction dependency chain, and the problem area is accurately located in the global scheduling framework. Specifically, first, the conflict information in the test result set is matched with the unique instruction identifier to determine the specific instruction node where the conflict occurs. Then, the upstream and downstream associations of the node in the dependency chain are tracked to identify the related instruction set affected by it. On this basis, the conflict node and its dependency chain segment are divided into a non-parallel domain, indicating that the instructions in this area must be executed in strict order. The nodes and chain segments not involving conflicts are divided into a rearrangeable domain, allowing flexible adjustment of the execution order under the premise of meeting the dependency constraints.

[0130] Step S3043: In the non-parallel domain, the related instructions are prioritized according to the control intention, prohibited boundary, and execution window to determine the instruction set of reserved instructions, delayed instructions, and replaced instructions.

[0131] In this embodiment, under the premise that there is an explicit instruction conflict in the non-parallel domain, the execution of different instructions needs to be decided through priority arbitration. Specifically, first, the conflict instructions are sorted according to the target state constraints defined in the control intention, and the instructions directly corresponding to the global control target are prioritized to be reserved. Second, combined with the prohibited boundary condition, the instructions that violate the safety mutual exclusion rule or trigger out-of-bound are excluded and marked as non-executable. Then, according to the time sequence arrangement of the execution window, the remaining instructions are scheduled in the time dimension. If the resource conflict in the same window cannot be resolved, some instructions are delayed to the subsequent window for execution. For instructions with functional substitution relationship, the substitute instruction that is logically equivalent but has more reasonable resource occupation is selected to relieve the conflict. It should be noted that the final result formed through this arbitration process is an instruction set containing reserved instructions, delayed instructions, and replaced instructions.

[0132] Step S3044: Under the constraints of the rearrangeable domain and the replaced instruction set, the instruction sequence that meets the dependency relationship and the execution window is reconstructed, and the executable manifest containing the instruction order, execution window, and mutual exclusion shielding rule is output.

[0133] In this embodiment, after priority arbitration, the instructions in the rearrangeable domain and the replacement instruction set are uniformly scheduled to generate a final executable instruction list; specifically, first, the instructions in the rearrangeable domain are reordered according to the dependency chain to ensure that all preconditions are met before the subsequent instructions are executed; second, the instructions in the replacement instruction set are merged with the original sequence to replace the instructions that are eliminated or delayed, thereby maintaining the integrity of the overall logic; then, under the constraints of the execution window, the instructions that can be executed in parallel are grouped, and mutual exclusion masking rules are introduced for instructions that have potential conflicts to avoid resource contention or logical contradictions; finally, the processed instructions are output in a structured form to form a list containing execution order, corresponding window and shielding constraints.

[0134] It should be noted that the list not only integrates the execution priority and replacement strategy after arbitration, but also realizes the operational expression of complex regulation tasks through timing and mutual exclusion rules.

[0135] Step S305: The executable list is issued to the corresponding execution end according to the hierarchy to realize multi-link joint regulation and control of the plant intelligent factory.

[0136] In this embodiment, after generating the executable list containing instruction sequence, execution window and mutual exclusion masking rules, it needs to be issued to the corresponding execution end according to the hierarchy to realize cross-hierarchy joint regulation and control; specifically, first, according to the preset hierarchy label in the instruction list, the device-level instructions are distributed to the single-machine control module, the cultivation unit-level instructions are distributed to the regional control node, and the workshop-level instructions are distributed to the global scheduling center; then, the instructions are synchronized and corrected during the issuing process to ensure that different hierarchy execution ends receive and execute operations under the same time reference; then, the received atomic instructions are converted into actual operation actions by calling the execution interface in each layer execution end, such as adjusting the light power or water pump flow in the device-level execution end, adjusting the local nutrient solution concentration in the cultivation unit-level execution end, and uniformly regulating the environment temperature and humidity in the workshop-level execution end; finally, the feedback information generated during the execution process is recycled and recorded to form the input basis of the closed-loop control.

[0137] It should be noted that the hierarchical issuance not only realizes the parallel joint of multi-link, but also ensures the consistency and traceability of the regulation and control actions in the global range of the plant intelligent factory through the coordination of upstream and downstream.

[0138] Embodiment 2

[0139] Please refer to Figure 4 Another embodiment provided by the present application: a plant intelligent factory multi-dimensional data monitoring and collaborative control system, comprising: a data acquisition module, an influence path identification module and a joint regulation and control module;

[0140] The data collection module is configured to collect multi-dimensional data of the plant intelligent factory in real time, wherein the multi-dimensional data comprises plant physiological parameters, environmental factor parameters, nutrient solution parameters, and equipment and operation state parameters.

[0141] The influence path identification module is configured to construct a dynamic multi-level causal correlation model among the equipment, plant physiology, environment, and operation based on the multi-dimensional data, and identify a potential synergistic influence path in an abnormal state.

[0142] The linkage control module is configured to automatically perform cross-level management and control when an abnormality is detected or a growth process deviates from a trend is predicted, distribute cross-level management and control instructions to the equipment level, the cultivation unit level, and the workshop level according to the levels, and perform multi-linkage control of the plant intelligent factory.

[0143] The linkage control module comprises an intention identification unit, an instruction generation unit, and a linkage control unit.

[0144] The intention identification unit is configured to determine a controlled object set and a forbidden boundary based on the potential synergistic influence path, and form a management and control intention comprising a target state constraint, a resource constraint, and a time sequence constraint.

[0145] The instruction generation unit is configured to decompose a management and control action into an atomic instruction sequence of the equipment level, the cultivation unit level, and the workshop level according to the management and control intention, and generate a complete instruction for cross-level scheduling and calling.

[0146] The linkage control unit is configured to distribute an executable list to a corresponding execution end according to the levels, and perform multi-linkage control of the plant intelligent factory.

[0147] In addition, the parts of the above technical solutions in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive repetition.

[0148] The specific embodiments described above further illustrate the purposes, technical solutions, and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, and the like made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for multi-dimensional data monitoring and collaborative management of a plant smart factory, characterized in that, The method comprises the following steps: Real-time acquisition of multi-dimensional data of a plant intelligent factory, including plant physiological parameters, environmental factor parameters, nutrient solution parameters, and equipment and operation state parameters; Based on the multi-dimensional data, a dynamic multi-level causal correlation model between equipment, plant physiology, environment, and operation is constructed, and potential synergistic influence paths in abnormal states are identified; When an anomaly is detected or a growth process is predicted to deviate from a trend, automatic cross-level management and control is performed, cross-level management and control instructions are distributed to the equipment level, the cultivation unit level, and the workshop level according to the level, and multi-link joint regulation and control of the plant intelligent factory is performed.

2. The plant smart factory multi-dimensional data monitoring and collaborative management method of claim 1, wherein, Based on the multi-dimensional data, a dynamic multi-level causal correlation model between equipment, plant physiology, environment, and operation is constructed, and potential synergistic influence paths in abnormal states are identified, comprising: The multi-dimensional data is hierarchically preprocessed according to the equipment parameter layer, the plant physiology layer, the environmental factor layer, and the operation layer, and the data in the same layer is normalized and time-synchronized; By establishing a multi-level feature index, key factors with potential coupling relationships between layers are identified, and a cross-layer correlation factor set is generated; According to the cross-layer correlation factor set, a time sequence interaction sequence between different level factors is constructed, which represents the factor sequence and transmission path in the dynamic change process; Based on the time sequence interaction sequence, the key factors of the equipment parameter layer, the plant physiology layer, the environmental factor layer, and the operation layer are mapped to a multi-level causal graph, and cross-layer action links are marked in the graph; In the multi-level causal graph, according to a preset path traversal logic, potential synergistic influence paths corresponding to abnormal states are extracted.

3. The plant smart factory multi-dimensional data monitoring and collaborative management method of claim 2, wherein, Based on the time sequence interaction sequence, the key factors of the equipment parameter layer, the plant physiology layer, the environmental factor layer, and the operation layer are mapped to a multi-level causal graph, and cross-layer action links are marked in the graph, comprising: The equipment factors, plant physiology factors, environmental factors, and operation factors in the time sequence interaction sequence are abstracted into graph nodes respectively, and each node is assigned a unique identifier; According to the time sequence dependency relationship between factors in the same level, intra-layer causal links are generated in the causal graph, which reflect the dynamic interaction logic between key factors in the same layer; Iterate the factor pairs with cross-layer time sequence dependency relationship, and establish cross-layer action links in the causal graph to mark the causal connection between different levels; The intra-layer causal links and cross-layer action links are structurally integrated to form a multi-level causal graph with hierarchical topological characteristics.

4. The plant smart factory multi-dimensional data monitoring and collaborative management method of claim 3, wherein, In the multi-level causal graph, according to a preset path traversal logic, potential synergistic influence paths corresponding to abnormal states are extracted, comprising: In the multi-level causal graph, according to the trigger information corresponding to the abnormal state, determine the nodes related to the abnormality as the traversal starting anchor point; Starting from the traversal starting anchor point, recursively according to the preset path traversal logic, sequentially access the successor nodes that have causal connection with the traversal starting anchor point to form a candidate path set; The causal consistency of the candidate path set is checked one by one, and paths inconsistent with the atlas logic or irrelevant to the abnormal state are excluded to generate effective paths meeting the constraint conditions; The effective paths are structured and collected to generate potential synergistic influence paths corresponding to the abnormal state.

5. The plant smart factory multi-dimensional data monitoring and collaborative management method of claim 1, wherein, When detecting an abnormality or predicting that the growth process deviates from the trend, automatic cross-level management is performed, and cross-level management instructions are distributed to the device level, the cultivation unit level, and the workshop level to perform multi-link joint regulation and control of the plant intelligent factory, including: The multi-source trigger information generated by abnormality detection or growth process prediction is merged and processed to generate a cross-level management event, and the cross-level management event is labeled with a scope, a time limit, and a priority tag; Based on the potential synergistic influence path, a set of controlled objects and a prohibited boundary are determined to form a management intent containing target state constraints, resource constraints, and timing constraints; According to the management intent, the management action is decomposed into atomic instruction sequences at the device level, the cultivation unit level, and the workshop level, the upstream and downstream dependency relationships and the execution window are established, and complete instructions for cross-layer scheduling are generated; The atomic instruction sequences are subjected to resource occupation, timing sequence, and safety mutual exclusion inspection, and when mutual exclusion is detected, priority arbitration and alternative sequence reconstruction are performed to generate an executable list meeting the constraint conditions; The executable list is distributed to the corresponding execution end according to the level to perform multi-link joint regulation and control of the plant intelligent factory.

6. The plant smart factory multi-dimensional data monitoring and collaborative management method of claim 5, wherein, Based on the potential synergistic influence path, a set of controlled objects and a prohibited boundary are determined to form a management intent containing target state constraints, resource constraints, and timing constraints, including: In the potential synergistic influence path, a set of controlled objects that need to be implemented for management are determined according to the node causal relationship, and each controlled object is independently indexed; For the set of controlled objects, a prohibited boundary is set to limit the range of operations that cannot be triggered according to the conflict conditions existing in the cross-layer action link; Combined with the set of controlled objects and the prohibited boundary, a set of management constraints containing target state constraints, resource constraints, and timing constraints is generated; The management constraint set is structured and integrated to form a complete management intent.

7. The plant smart factory multi-dimensional data monitoring and collaborative management method of claim 6, wherein, According to the management intent, the management action is decomposed into atomic instruction sequences at the device level, the cultivation unit level, and the workshop level, the upstream and downstream dependency relationships and the execution window are established, and complete instructions for cross-layer scheduling are generated, including: The management intent is parsed into atomic instruction sequences at the device level, the cultivation unit level, and the workshop level, and each instruction is assigned a unique identifier; According to the trigger sequence and resource occupation conditions in the atomic instruction sequence, an upstream and downstream dependency relationship chain is established; Combined with the dependency relationship chain, the corresponding execution window is divided according to the time interval and parallelism constraint, and each instruction is mapped to the corresponding execution window; The mapped atomic instructions, their dependency relationships, and execution windows are serialized and collected to generate complete instructions for cross-layer scheduling.

8. The plant smart factory multi-dimensional data monitoring and collaborative management method of claim 7, wherein, The atomic instruction sequences are subjected to resource occupation, timing sequence, and safety mutual exclusion inspection, and when mutual exclusion is detected, priority arbitration and alternative sequence reconstruction are performed to generate an executable list meeting the constraint conditions, including: The atomic instruction sequence is checked for resource occupation, timing sequence and safety mutual exclusion, and a verification result set containing conflict markers and trigger conditions is generated; The verification result set is mapped to an instruction dependency chain, and the conflicting instruction nodes and their upstream and downstream associated nodes are located, and the non-parallel domain and the rearrangeable domain are divided accordingly; In the non-parallel domain, priority arbitration is performed on related instructions according to control intention, prohibited boundary and execution window, and the instruction set of reserved instructions, delayed instructions and replacement instructions is determined; Under the constraints of the rearrangeable domain and the replacement instruction set, the instruction sequence that meets the dependency relationship and the execution window is reconstructed, and the executable manifest containing the instruction sequence, the execution window and the mutual exclusion shielding rule is output.

9. The plant intelligent factory multi-dimensional data monitoring and collaborative management system, used for realizing the plant intelligent factory multi-dimensional data monitoring and collaborative management method in any one of claims 1-8, characterized in that, It comprises: a data acquisition module, an influence path identification module, and a linkage control module; The data acquisition module is configured to acquire multi-dimensional data of the plant intelligent factory in real time, wherein the multi-dimensional data comprises plant physiological parameters, environmental factor parameters, nutrient solution parameters, and equipment and operation state parameters; The influence path identification module is configured to construct a dynamic multi-level causal association model among equipment, plant physiology, environment, and operation based on the multi-dimensional data, and identify potential synergistic influence paths in abnormal states; The linkage control module is configured to automatically perform cross-level control when an abnormality is detected or a growth process deviating trend is predicted, and distribute cross-level control instructions to the equipment level, the cultivation unit level, and the workshop level according to the level, and perform multi-linkage control of the plant intelligent factory. 10.The plant smart factory multi-dimensional data monitoring and collaborative management system of claim 9, wherein, The linkage control module comprises an intention identification unit, an instruction generation unit, and a linkage control unit; The intention identification unit is configured to determine a controlled object set and a prohibited boundary based on the potential synergistic influence path, and form a control intention containing target state constraints, resource constraints, and timing constraints; The instruction generation unit is configured to decompose control actions into atomic instruction sequences of the equipment level, the cultivation unit level, and the workshop level according to the control intention, and generate complete instructions for cross-level scheduling calls; The linkage control unit is configured to distribute executable manifests to corresponding execution ends according to the level, and perform multi-linkage control of the plant intelligent factory.

Images