A production line equipment life cycle perception method and device based on equipment tree

Abstract

The present application relates to a method and device for perceiving the lifecycle of production line equipment based on a device tree, including real-time extraction of operation data in operation messages, data association and attribution according to the device tree model and segmentation granularity of the production line, discrete model analysis of standardized mechanism models, application scenarios, environmental parameters, special data collection, and alarm data, and determination of the health index of the production line equipment; thereby obtaining the lifecycle of the production line equipment. It realizes the establishment of a device tree model and architecture with segmentation granularity, and the segmentation dimension of the production line equipment can be infinitely refined and systematized; establishes a scientific and segmentation granular expert experience library; performs data association and attribution according to the device tree model and segmentation granularity of the production line, and performs discrete model analysis on the big data of standardized mechanism models, application scenarios, environmental parameters, special data collection, and alarm data according to the type, and associates the system expert library to obtain the lifecycle of the production line equipment.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for perceiving the lifecycle of production line equipment based on a device tree. Background Art

[0002] An industrial robot is a multi-joint manipulator or multi-degree-of-freedom machine device for the industrial field. It can perform work automatically and relies on its own power and control capabilities to achieve various functions.

[0003] In the modern manufacturing industry, professional technicians can connect robots, automated production equipment, transmission lines, control systems, etc. in series according to the requirements of production processes through overall planning and design, and build automated production lines based on robot applications. Automated production lines can run according to pre-programmed programs to achieve automated production and unmanned production.

[0004] Automated production lines based on robot applications can replace humans in industrial production to do certain monotonous, frequent and repetitive long-term operations, or operations in dangerous and harsh environments. For example, in production process links such as stamping, welding, painting, machining, casting, heat treatment, and automated assembly, they can replace humans and realize automated production.

[0005] As the degree of automation of automated production lines based on robot applications increases and the number of robots and automated equipment increases, the "focus" of production management shifts from "managing people" to "managing equipment."

[0006] How to avoid and reduce the losses caused by abnormal downtime, how to reasonably and adequately plan spare parts reserves, how to accurately predict equipment risks and life cycles, how to arrange equipment overhaul and maintenance, how to formulate emergency plans for equipment downtime, how to achieve predictive maintenance management of production line equipment, etc., have become the top technical and management tasks that the production and equipment management departments of manufacturing companies urgently need to solve.

[0007] At present, due to the lack of mature technology to accurately perceive and analyze the life cycle and health status of automated production line equipment, the preventive or predictive maintenance of equipment cannot be carried out reasonably, scientifically and effectively. Abnormal shutdown of production lines causes huge direct and indirect production economic losses and waste of resources.

[0008] How to timely discover or predict the life cycle and health status of automated production line equipment, including robots, is a technical problem that urgently needs to be solved. Summary of the invention

[0009] The technical problem to be solved by the present application is to provide a method and device for perceiving the life cycle of production line equipment based on a device tree in view of the deficiencies in the prior art.

[0010] The technical solution of this application to solve the above technical problems is as follows:

[0011] In a first aspect, the present application provides a production line equipment lifecycle perception method based on a device tree, the method comprising:

[0012] Establishing a device tree of production line equipment, and establishing an expert library of the device tree using historical operation data of the production line equipment;

[0013] Extract operation data from operation messages in real time, associate and attribute data according to the equipment tree model and segmentation granularity of the production line, implement standardized mechanism models, application scenarios, environmental parameters, collect special data and alarm data according to types, perform discrete model analysis, and determine the health index of production line equipment;

[0014] According to the expert library of the health index-associated equipment tree, the life cycle of the production line equipment is obtained.

[0015] In a second aspect, the present application provides a production line equipment lifecycle perception device based on a device tree, the device comprising:

[0016] A first processing module is used to establish a device tree of production line equipment and to establish an expert library of the device tree using historical operation data of the production line equipment;

[0017] The second processing module is used to extract the operation data in the operation message in real time, perform data association and attribution according to the equipment tree model and segmentation granularity of the production line, implement standardized mechanism models, application scenarios, environmental parameters, collect special data and alarm data according to the type, perform discrete model analysis, and determine the health index of the production line equipment;

[0018] The third processing module is used to obtain the life cycle of the production line equipment according to the expert library of the health index-associated equipment tree.

[0019] The beneficial effects of this application are: a method for perceiving the life cycle of production line equipment based on a device tree is proposed, which realizes the establishment of a device tree model and architecture with segmented granularity, and the segmented dimensions of production line equipment can be infinitely refined and systematized, such as: production base, workshop, production line, process section, workstation, complete set of equipment, equipment, parts, combination kits, components, etc.; establish a scientific and segmented granular expert experience library; according to the equipment tree model and segmented granularity of the production line, data association and attribution are performed, and standardized mechanism models, application scenarios, environmental parameters, and big data discrete model analysis of special data and alarm data are realized according to the type, and the associated system expert library is associated. This application can effectively and accurately perceive the remaining life cycle of automated production line equipment through this automated production line equipment life cycle perception method based on the device tree model algorithm, and reasonably arrange preventive or predictive maintenance plans for the production and equipment management departments of manufacturing enterprises, providing intelligent decision-making and data support. And it can achieve the following revolutionary technical effects: 1. Accurately locate and evaluate equipment failure points and risk points; 2. Accurately predict the changing trend of equipment risks; 3. Accurately predict equipment risk points to reduce the risk of sudden failure and downtime; 4. Realize the small-scale, comprehensive and systematic analysis of equipment risk data; 5. Realize early warning of equipment risks.

[0020] Advantages of additional aspects of the present application will be given in part in the following description, and in part will become apparent from the following description, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A schematic diagram of a process flow of a production line equipment lifecycle perception method based on a device tree according to an embodiment of the present application;

[0023] Figure 2 This is a module diagram of a device tree-based production line equipment lifecycle perception device according to another embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0025] like Figure 1 The method for perceiving the lifecycle of a production line device based on a device tree according to an embodiment of the present application comprises the following steps:

[0026] 110. Establish a device tree for production line equipment, and establish an expert database for the device tree using historical operation data of the production line equipment.

[0027] 120. Extract the operation data from the operation message in real time, associate and attribute the data according to the equipment tree model and segmentation granularity of the production line, implement standardized mechanism models, application scenarios, environmental parameters, collect special data and alarm data according to the type, perform discrete model analysis, and determine the health index of the production line equipment.

[0028] 130. According to the expert library of the health index-associated equipment tree, the life cycle of the production line equipment is obtained.

[0029] Based on the above embodiment, further, the establishing of the equipment tree of the production line equipment specifically includes:

[0030] Obtaining a component unit of the production line equipment, wherein the component unit includes a motor, a gear box, a control cabinet, a track and a transmission mechanism;

[0031] Get all the unit components of each component unit;

[0032] The equipment tree of the production line equipment is constructed by taking the production line equipment as the root node, the component composition unit as the stem node, and all the unit components in each component composition unit as the leaf nodes.

[0033] Based on the above embodiment, further, the use of the historical operation data of the production line equipment to establish the expert library of the equipment tree specifically includes:

[0034] Taking the leaf nodes as objects, retrieving the historical operation data, and obtaining the original operation data of each leaf node;

[0035] Taking the stem node as an object, retrieving the historical operation data, and obtaining the original operation data of each stem node;

[0036] Aggregating the original operation data of all leaf nodes under each of the stem nodes into the original operation data of the stem node;

[0037] Based on the special data of the stem node, the original operation data of the leaf nodes under the stem node are filtered, and the original operation data of the stem node is filtered;

[0038] Establishing an expert database for the operation data type of the filtered original operation data of the stem node;

[0039] Using the original operation data of the leaf nodes, calculate the risk score value of each operation data type of all leaf nodes under the stem node, and the time life value of each leaf node;

[0040] Obtaining a risk score value of each operating data type of the stem node according to the risk score value of each operating data type of all leaf nodes under the stem node;

[0041] Obtaining the time life value of the stem node according to the time life values ​​of all leaf nodes under the stem node;

[0042] The risk score values ​​of each operating data type of all the stem nodes and the time life value of the stem nodes are summarized in the expert library, and the risk score values ​​of each operating data type of all the leaf nodes and the time life value of the leaf nodes are summarized in the expert library to obtain the expert library of the device tree.

[0043] Based on the above embodiment, the real-time extraction of operation data in the operation message is performed according to the equipment tree model and segmentation granularity of the production line, and data association and attribution are performed. The mechanism model, application scenario, environmental parameters, and big data of special data and alarm data that are standardized according to the type are performed, and discrete model analysis is performed to determine the health index of the production line equipment, specifically including:

[0044] Extracting unit components and component constituent units to which the unit components belong in the operation data;

[0045] Matching the unit components to leaf nodes in the device tree, and matching the component constituent units to stem nodes in the device tree;

[0046] Traversing the device tree, determining whether the component component unit exists in the device tree, and if so, searching for the unit component under the stem node corresponding to the component component unit, and if found, saving the real-time operation data of the unit component to the expert database;

[0047] If not found, a new leaf node is created under the stem node, and the mechanism model, application scenario, environmental parameters, special data and alarm data of the unit components of the same type as the new leaf node in the device tree are determined;

[0048] If there is no unit component of the same type as the newly created leaf node in the device tree, then according to preset rules, the mechanism model, application scenario, environmental parameters, collection of special data and alarm data of the newly created leaf node are set;

[0049] If the component unit does not exist in the device tree, a new stem node is created under the root node, and a new leaf node is created under the new stem node. Based on the mechanism model, application scenario, environmental parameter, special collection data and alarm data of the component unit of the same type as the new stem node in the device tree, the mechanism model, application scenario, environmental parameter, special collection data and alarm data of the new stem node are determined. If the unit component of the same type as the new stem node does not exist in the device tree, the mechanism model, application scenario, environmental parameter, special collection data and alarm data of each operating data type of the new stem node are set according to preset rules.

[0050] The equipment tree is input into the discrete model to obtain the health index of the production line equipment.

[0051] Based on the above embodiment, further, the mechanism model, application scenario, environmental parameter, special data collection and alarm data of the component component unit of the same type as the newly created stem node in the device tree are determined, specifically including:

[0052] According to the mechanism models, application scenarios, environmental parameters, special collection data and alarm data of all leaf nodes under the stem node of the equipment tree, the mechanism model, application scenarios, environmental parameters, special collection data and alarm data of the newly created stem node are obtained.

[0053] Based on the above embodiment, further, the mechanism model, application scenario, environmental parameter, special data collection and alarm data of all leaf nodes under the stem node of the device tree are obtained, specifically including:

[0054] Inputting the environmental parameters of all leaf nodes under the stem node of the device tree into a preset statistical formula respectively to obtain the environmental parameters of the newly created stem node;

[0055] Inputting the collection-specific data and alarm data of all leaf nodes under the stem node of the device tree into a preset statistical formula respectively to obtain the collection-specific data of the stem node;

[0056] Inputting the alarm data of all leaf nodes under the stem node of the device tree into a preset statistical formula respectively to obtain the alarm data of the stem node;

[0057] Determine the mechanism model of the stem node according to the mechanism models of all leaf nodes under the stem node of the device tree;

[0058] The application scenario of the stem node is determined according to the application scenarios of all leaf nodes under the stem node of the device tree.

[0059] Based on the above-mentioned embodiment, a production line equipment lifecycle perception method based on a device tree is proposed, which realizes the establishment of a device tree model and architecture with subdivided granularity, and the subdivided dimensions of the production line equipment can be infinitely refined and systematized, such as: production base, workshop, production line, process section, workstation, complete set of equipment, equipment, parts, combination kits, components, etc.; establish a scientific, subdivided granular expert experience library; according to the equipment tree model and subdivided granularity of the production line, perform data association and attribution, and implement standardized mechanism models, application scenarios, environmental parameters, and big data discrete model analysis of special data and alarm data according to type, and associate system expert libraries. This application uses this automated production line equipment lifecycle perception method based on the device tree model algorithm to effectively and accurately perceive the remaining life cycle of automated production line equipment, and reasonably arrange preventive or predictive maintenance plans for the production and equipment management departments of manufacturing enterprises, providing intelligent decision-making and data support. And it can achieve the following revolutionary technical effects: 1. Accurately locate and evaluate equipment failure points and risk points; 2. Accurately predict the changing trend of equipment risks; 3. Accurately predict equipment risk points to reduce the risk of sudden failure and downtime; 4. Realize the small-scale, comprehensive and systematic analysis of equipment risk data; 5. Realize early warning of equipment risks.

[0060] like Figure 2 As shown, a production line equipment life cycle perception device based on a device tree, the device comprising:

[0061] A first processing module is used to establish a device tree of production line equipment and to establish an expert library of the device tree using historical operation data of the production line equipment;

[0062] The second processing module is used to extract the operation data in the operation message in real time, perform data association and attribution according to the equipment tree model and segmentation granularity of the production line, implement standardized mechanism models, application scenarios, environmental parameters, collect special data and alarm data according to the type, perform discrete model analysis, and determine the health index of the production line equipment;

[0063] The third processing module is used to obtain the life cycle of the production line equipment according to the expert library of the health index-associated equipment tree.

[0064] Based on the above embodiment, further, the first processing module is specifically used to obtain a component unit of the production line equipment, and the component unit includes a motor, a gear box, a control cabinet, a track and a transmission mechanism;

[0065] Get all the unit components of each component unit;

[0066] The equipment tree of the production line equipment is constructed by taking the production line equipment as the root node, the component composition unit as the stem node, and all the unit components in each component composition unit as the leaf nodes.

[0067] Based on the above embodiment, further, the first processing module is specifically used to retrieve the historical operation data with the leaf node as the object, and obtain the original operation data of each leaf node;

[0068] Taking the stem node as an object, retrieving the historical operation data, and obtaining the original operation data of each stem node;

[0069] Aggregating the original operation data of all leaf nodes under each of the stem nodes into the original operation data of the stem node;

[0070] Based on the special data of the stem node, the original operation data of the leaf nodes under the stem node are filtered, and the original operation data of the stem node is filtered;

[0071] Establishing an expert database for the operation data type of the filtered original operation data of the stem node;

[0072] Using the original operation data of the leaf nodes, calculate the risk score value of each operation data type of all leaf nodes under the stem node, and the time life value of each leaf node;

[0073] Obtaining a risk score value of each operating data type of the stem node according to the risk score value of each operating data type of all leaf nodes under the stem node;

[0074] Obtaining the time life value of the stem node according to the time life values ​​of all leaf nodes under the stem node;

[0075] The risk score values ​​of each operating data type of all the stem nodes and the time life value of the stem nodes are summarized in the expert library, and the risk score values ​​of each operating data type of all the leaf nodes and the time life value of the leaf nodes are summarized in the expert library to obtain the expert library of the device tree.

[0076] Based on the above embodiment, further, the feature is that:

[0077] The second processing module is specifically used to extract the unit components and the component constituent units to which the unit components belong in the operation data;

[0078] Matching the unit components to leaf nodes in the device tree, and matching the component constituent units to stem nodes in the device tree;

[0079] Traversing the device tree, determining whether the component component unit exists in the device tree, and if so, searching for the unit component under the stem node corresponding to the component component unit, and if found, saving the real-time operation data of the unit component to the expert database;

[0080] If not found, a new leaf node is created under the stem node, and the mechanism model, application scenario, environmental parameters, special data and alarm data of the unit components of the same type as the new leaf node in the device tree are determined;

[0081] If there is no unit component of the same type as the newly created leaf node in the device tree, then according to preset rules, the mechanism model, application scenario, environmental parameters, collection of special data and alarm data of the newly created leaf node are set;

[0082] If the component unit does not exist in the device tree, a new stem node is created under the root node, and a new leaf node is created under the new stem node. Based on the mechanism model, application scenario, environmental parameter, special collection data and alarm data of the component unit of the same type as the new stem node in the device tree, the mechanism model, application scenario, environmental parameter, special collection data and alarm data of the new stem node are determined. If the unit component of the same type as the new stem node does not exist in the device tree, the mechanism model, application scenario, environmental parameter, special collection data and alarm data of each operating data type of the new stem node are set according to preset rules.

[0083] The equipment tree is input into the discrete model to obtain the health index of the production line equipment.

[0084] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A production line equipment life cycle perception method based on device tree, characterized in that: The method comprises: Establishing a device tree of production line equipment, and establishing an expert library of the device tree using historical operation data of the production line equipment; Extract operation data from operation messages in real time, associate and attribute data according to the equipment tree model and segmentation granularity of the production line, implement standardized mechanism models, application scenarios, environmental parameters, collect special data and alarm data according to types, perform discrete model analysis, and determine the health index of production line equipment; According to the expert database of the health index-related equipment tree, the life cycle of the production line equipment is obtained; The step of establishing a device tree for production line equipment specifically includes: Obtaining a component unit of the production line equipment, wherein the component unit includes a motor, a gear box, a control cabinet, a track and a transmission mechanism; Get all the unit components of each component unit; The equipment tree of the production line equipment is constructed by taking the production line equipment as the root node, the component composition unit as the stem node, and all the unit components in each component composition unit as the leaf nodes; The method of establishing the equipment tree expert library by using the historical operation data of the production line equipment specifically includes: Taking the leaf nodes as objects, retrieving the historical operation data, and obtaining the original operation data of each leaf node; Taking the stem node as an object, retrieving the historical operation data, and obtaining the original operation data of each stem node; Aggregating the original operation data of all leaf nodes under each of the stem nodes into the original operation data of the stem node; Based on the special data of the stem node, the original operation data of the leaf nodes under the stem node are filtered, and the original operation data of the stem node is filtered; Establishing an expert database for the operation data type of the filtered original operation data of the stem node; Using the original operation data of the leaf nodes, calculate the risk score value of each operation data type of all leaf nodes under the stem node, and the time life value of each leaf node; Obtaining a risk score value of each operating data type of the stem node according to the risk score value of each operating data type of all leaf nodes under the stem node; Obtaining the time life value of the stem node according to the time life values ​​of all leaf nodes under the stem node; Aggregating the risk score values ​​of each operating data type of all the stem nodes and the time life value of the stem nodes into the expert database, and aggregating the risk score values ​​of each operating data type of all the leaf nodes and the time life value of the leaf nodes into the expert database, to obtain the expert database of the device tree; The real-time extraction of operation data in the operation message is carried out, data association and attribution are carried out according to the equipment tree model and segmentation granularity of the production line, and the mechanism model, application scenario, environmental parameters, and big data of special data and alarm data that are standardized according to the type are carried out, and discrete model analysis is carried out to determine the health index of the production line equipment, specifically including: Extracting unit components and component constituent units to which the unit components belong in the operation data; Matching the unit components to leaf nodes in the device tree, and matching the component constituent units to stem nodes in the device tree; Traversing the device tree, determining whether the component component unit exists in the device tree, and if so, searching for the unit component under the stem node corresponding to the component component unit, and if found, saving the real-time operation data of the unit component to the expert database; If not found, a new leaf node is created under the stem node, and the mechanism model, application scenario, environmental parameters, special data and alarm data of the unit components of the same type as the new leaf node in the device tree are determined; If there is no unit component of the same type as the newly created leaf node in the device tree, then according to preset rules, the mechanism model, application scenario, environmental parameters, collection of special data and alarm data of the newly created leaf node are set; If the component unit does not exist in the device tree, a new stem node is created under the root node, and a new leaf node is created under the new stem node. Based on the mechanism model, application scenario, environmental parameter, special collection data and alarm data of the component unit of the same type as the new stem node in the device tree, the mechanism model, application scenario, environmental parameter, special collection data and alarm data of the new stem node are determined. If the unit component of the same type as the new stem node does not exist in the device tree, the mechanism model, application scenario, environmental parameter, special collection data and alarm data of each operating data type of the new stem node are set according to preset rules. The equipment tree is input into the discrete model to obtain the health index of the production line equipment.

2. The method for perceiving the life cycle of production line equipment based on equipment tree according to claim 1, characterized in that: The determining of the mechanism model, application scenario, environmental parameter, collection of special data and alarm data of the newly created stem node based on the mechanism model, application scenario, environmental parameter, collection of special data and alarm data of the component component unit of the same type as the newly created stem node in the device tree specifically includes: According to the mechanism models, application scenarios, environmental parameters, special collection data and alarm data of all leaf nodes under the stem node of the equipment tree, the mechanism model, application scenarios, environmental parameters, special collection data and alarm data of the newly created stem node are obtained.

3. The method for perceiving the life cycle of production line equipment based on equipment tree according to claim 2, characterized in that: The mechanism model, application scenario, environmental parameter, special data collection and alarm data of all leaf nodes under the stem node of the device tree are obtained, specifically including: Inputting the environmental parameters of all leaf nodes under the stem node of the device tree into a preset statistical formula respectively to obtain the environmental parameters of the newly created stem node; Inputting the collection-specific data and alarm data of all leaf nodes under the stem node of the device tree into a preset statistical formula respectively to obtain the collection-specific data of the stem node; Inputting the alarm data of all leaf nodes under the stem node of the device tree into a preset statistical formula respectively to obtain the alarm data of the stem node; Determine the mechanism model of the stem node according to the mechanism models of all leaf nodes under the stem node of the device tree; The application scenario of the stem node is determined according to the application scenarios of all leaf nodes under the stem node of the device tree.

4. A production line equipment life cycle perception device based on equipment tree, characterized in that: The device comprises: A first processing module is used to establish a device tree of production line equipment and to establish an expert library of the device tree using historical operation data of the production line equipment; The second processing module is used to extract the operation data in the operation message in real time, perform data association and attribution according to the equipment tree model and segmentation granularity of the production line, implement standardized mechanism models, application scenarios, environmental parameters, collect special data and alarm data according to the type, perform discrete model analysis, and determine the health index of the production line equipment; The third processing module is used to obtain the life cycle of the production line equipment according to the expert library of the health index-associated equipment tree; The first processing module is specifically used to obtain a component unit of the production line equipment, wherein the component unit includes a motor, a gear box, a control cabinet, a track and a transmission mechanism; Get all the unit components of each component unit; The equipment tree of the production line equipment is constructed by taking the production line equipment as the root node, the component composition unit as the stem node, and all the unit components in each component composition unit as the leaf nodes; The first processing module is specifically used to retrieve the historical operation data with the leaf node as the object, and obtain the original operation data of each leaf node; Taking the stem node as an object, retrieving the historical operation data, and obtaining the original operation data of each stem node; Aggregating the original operation data of all leaf nodes under each of the stem nodes into the original operation data of the stem node; Based on the special data of the stem node, the original operation data of the leaf nodes under the stem node are filtered, and the original operation data of the stem node is filtered; Establishing an expert database for the operation data type of the filtered original operation data of the stem node; Using the original operation data of the leaf nodes, calculate the risk score value of each operation data type of all leaf nodes under the stem node, and the time life value of each leaf node; Obtaining a risk score value of each operating data type of the stem node according to the risk score value of each operating data type of all leaf nodes under the stem node; Obtaining the time life value of the stem node according to the time life values ​​of all leaf nodes under the stem node; Aggregating the risk score values ​​of each operating data type of all the stem nodes and the time life value of the stem nodes into the expert database, and aggregating the risk score values ​​of each operating data type of all the leaf nodes and the time life value of the leaf nodes into the expert database, to obtain the expert database of the device tree; The second processing module is specifically used to extract the unit components and the component constituent units to which the unit components belong in the operation data; Matching the unit components to leaf nodes in the device tree, and matching the component constituent units to stem nodes in the device tree; Traversing the device tree, determining whether the component component unit exists in the device tree, and if so, searching for the unit component under the stem node corresponding to the component component unit, and if found, saving the real-time operation data of the unit component to the expert database; If not found, a new leaf node is created under the stem node, and the mechanism model, application scenario, environmental parameters, special data and alarm data of the unit components of the same type as the new leaf node in the device tree are determined; If there is no unit component of the same type as the newly created leaf node in the device tree, then according to preset rules, the mechanism model, application scenario, environmental parameters, collection of special data and alarm data of the newly created leaf node are set; If the component unit does not exist in the device tree, a new stem node is created under the root node, and a new leaf node is created under the new stem node. Based on the mechanism model, application scenario, environmental parameter, special collection data and alarm data of the component unit of the same type as the new stem node in the device tree, the mechanism model, application scenario, environmental parameter, special collection data and alarm data of the new stem node are determined. If the unit component of the same type as the new stem node does not exist in the device tree, the mechanism model, application scenario, environmental parameter, special collection data and alarm data of each operating data type of the new stem node are set according to preset rules. The equipment tree is input into the discrete model to obtain the health index of the production line equipment.

Images