Property material management system and method based on Internet of Things technology

Through the property material management system with Internet of Things technology, faulty equipment identification model and path planning algorithm are used to solve the problems of low efficiency of material management and insufficient equipment maintenance in emergencies, and rapid response and risk reduction are achieved.

CN118941208AInactive Publication Date: 2024-11-12INHENG TECHNOLOGY (SHANGHAI) CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411010673.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing material management system is difficult to respond quickly in emergencies, especially in the event of fires or water inlets, and it cannot effectively reduce the risk of accidents. There are insufficient identification and maintenance of equipment failures, resulting in low management efficiency.

Method used

The property material management system based on the Internet of Things technology is adopted to identify equipment failures through the faulty equipment identification model, generate maintenance plans, and use path planning algorithms to output material collection paths to improve emergency response speed and equipment maintenance efficiency.

Benefits of technology

It has achieved rapid response to emergencies, reduced the risk of accidents, improved the pertinence and efficiency of equipment maintenance, and ensured the rational use of material management and risk control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941208A_ABST
    Figure CN118941208A_ABST
Patent Text Reader

Abstract

The invention discloses a property material management system and method based on the Internet of Things technology, and relates to the technical field of material management. RFID tags for storing related information are distributed for equipment materials, a sensor network is used for collecting equipment operation state data, a fault equipment identification model is used for carrying out fault identification on equipment, and if an operation fault exists, the system and the method are used for managing the equipment materials. A corresponding maintenance scheme is given for the fault equipment through the fault equipment maintenance knowledge graph, corresponding maintenance information is recorded, a maintenance coefficient of the fault equipment is generated through maintenance data of the fault equipment in an equipment maintenance period, and if the maintenance coefficient exceeds the expectation, periodic maintenance is carried out on the equipment; matching a corresponding material and equipment demand scheme for the emergency, and outputting a material collection path through a path planning algorithm according to equipment material data corresponding to the material and equipment demand scheme; and the demand scheme library matches the corresponding material equipment demand scheme for the emergency, so that the emergency response speed is accelerated during material management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of material management, and in particular to a property material management system and method based on the Internet of Things technology. Background Art

[0002] Material management based on the Internet of Things is a model that uses the Internet of Things technology to achieve intelligent and automated management of materials. The Internet of Things connects objects, equipment, people and things through Internet technology, making these objects and equipment have intelligent functions and can interact with people for data and information transmission. In the field of material management, the application of the Internet of Things technology has greatly improved the efficiency and accuracy of management. The Internet of Things technology enables real-time monitoring of material management, and managers can understand the inventory, usage and transportation of materials at any time. At the same time, the system can also set up an early warning mechanism. When the material inventory is lower than the safety inventory or an abnormal situation occurs, an early warning message will be automatically issued to remind managers to deal with it in time.

[0003] In the Chinese invention patent with application publication number CN111695788A, an emergency material management system based on the Internet of Things is disclosed. The emergency material management system based on the Internet of Things includes an image collector, a smart card reader, an Internet of Things RFID tag, a smart mobile device and a monitoring and management platform. The image collector is used to monitor the storage status of materials, and the smart card reader is used to obtain the material information in the Internet of Things RFID tag on each material and transmit it to the monitoring and management platform. The monitoring and management platform dynamically reflects the material entry and exit management, inventory management, and material information management, establishes corresponding permissions in combination with operations and working conditions, generates corresponding reports and warnings, and sends material operation information to the smart mobile device to perform corresponding material operations, thereby realizing rapid entry and exit operations of a large number of materials and improving the guarantee capability of emergency materials in emergency states.

[0004] Combined with the above application and the contents of the prior art:

[0005] When managing various materials in the building area, it is usually necessary to record and count the various materials and equipment in the management area, and then replenish them after they are damaged or consumed. In addition, in order to further improve the management precision, the status and location of various materials and equipment will be monitored and collected in real time, and an alarm will be issued to the outside when an abnormality occurs, so as to facilitate timely processing;

[0006] However, when alarms are issued frequently in the area involved, the material management area has a greater demand for various materials and equipment. In particular, when emergencies occur in the material management area, such as fire or water intrusion, the existing material management methods can only provide location information of materials and equipment and cannot respond quickly, resulting in the inability to implement emergency response when emergencies actually occur, making it difficult to reduce the risk of accidents caused by emergencies when they occur.

[0007] To this end, the present invention provides a property material management system and method based on Internet of Things technology. Summary of the invention

[0008] 1. Technical issues to be solved

[0009] In view of the deficiencies in the prior art, the present invention provides a property material management system and method based on the Internet of Things technology. The faults of the equipment are identified by using a faulty equipment identification model. If there is an operating fault, a corresponding maintenance plan is given to the faulty equipment by a faulty equipment maintenance knowledge graph, and corresponding maintenance information is recorded. The maintenance coefficient of the faulty equipment is generated by the maintenance data of the faulty equipment within the equipment maintenance cycle. If the maintenance coefficient exceeds expectations, the equipment is periodically maintained. A corresponding material and equipment demand plan is matched for the emergency, and a material collection path is output by a path planning algorithm based on the equipment material data corresponding to the material and equipment demand plan. A corresponding material and equipment demand plan is matched for the emergency, and the speed of emergency response is accelerated when performing material management, thereby solving the technical problems raised in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] The property material management method based on the Internet of Things technology includes collecting alarm information in a material management area and constructing a regional alarm information set, generating an alarm density Mjp from the regional alarm information set, and issuing a prompt instruction to the outside if the alarm density Mjp exceeds a density threshold;

[0013] After allocating RFID tags that store relevant information to equipment and materials, real-time monitoring is performed to obtain the corresponding location information, and the area where the equipment and materials are located is used as the storage area, and the location of the storage area is constrained; the method of constraining the location of the storage area is as follows:

[0014]

[0015] Where k is the number of storage areas, Z ij is the shortest distance from the i-th storage area to the j-th storage area, Z ais the average distance, Mjp is the alarm density;

[0016] The configured sensor network collects the equipment operation status data, and generates the abnormality degree Ypj of the equipment operation from the operation status data. If the abnormality degree Ypj exceeds the abnormal threshold, the fault equipment identification model is used to identify the equipment fault. If there is an operation fault, a fault maintenance instruction is issued to the outside.

[0017] The faulty equipment maintenance knowledge graph provides a corresponding maintenance plan for the faulty equipment and records the corresponding maintenance information. The maintenance coefficient Hts of the faulty equipment is generated from the maintenance data of the faulty equipment within the equipment maintenance cycle. If the maintenance coefficient Hts exceeds the frequency threshold, several equally spaced maintenance nodes are set within the equipment maintenance cycle.

[0018] The demand plan library matches the corresponding material and equipment demand plan for the emergency, and the path planning algorithm outputs the material collection path based on the equipment and material data corresponding to the material and equipment demand plan. After verifying the feasibility of the material collection path, it is used as the target path and marked on the electronic map.

[0019] Furthermore, after selecting the property material management area, the alarm information sent to the outside from the material management area is collected during the observation period, and the acquired alarm information is aggregated to construct a regional alarm information set;

[0020] The alarm density Mjp is constructed from the alarm information in the regional alarm information set in the following way:

[0021]

[0022] Where n is the number of alarms issued, L(i,j) is the shortest distance between the i-th alarm area and the j-th alarm area, and L a is the average distance, V(i,j) is the time interval from the i-th alarm to the j-th alarm, V a is the average value of the time interval; weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1.

[0023] Furthermore, after receiving the prompt instruction, the equipment and materials in the material management area are counted, and RFID tags are assigned to the equipment and materials. The RFID tags store the relevant information of the materials, and the location of the equipment and materials is updated in real time;

[0024] Construct an electronic map covering the material management area, mark equipment and material pairs based on location data, use the area where the materials and equipment are located as the storage area, constrain the location of the storage area, select the storage area within the material management area based on the constraints, and adjust the location of the current materials and equipment.

[0025] Furthermore, a sensor network is set on the device, and the sensor network monitors the operating status and environmental conditions of the device, and the acquired device operating status data is aggregated to generate a device operating data set;

[0026] The abnormality degree Ypj of the equipment during operation is generated by the equipment operation status data set. If the abnormality degree Ypj exceeds the abnormal threshold, a fault identification instruction is issued to the outside.

[0027] Furthermore, after linear normalization processing is performed on the acquired equipment operation data, the abnormality degree Ypj during equipment operation is generated in the following manner:

[0028]

[0029] Weight coefficient: 0≤F1≤1, 0≤F2≤1 and F2+F1=1; i=1, 2, …, n, where n is the number of monitoring nodes; P i Refers to the equipment operating parameters at the i-th monitoring node, P b is the preset standard value of the equipment operating parameters; Po is the median value of abnormality, Po i is the median value of the abnormality of the operating parameters of the i-th device, Po a is its mean, i=1, 2,…, m, and m is the number of equipment operating parameters.

[0030] Furthermore, after receiving the fault identification instruction, the equipment operation data and environmental condition data are used as input, and the equipment fault is identified using the trained fault equipment identification model; if the equipment currently has an operating fault, it is treated as a faulty device and the corresponding location data is marked on the electronic map, and a fault maintenance instruction is issued to the outside.

[0031] Furthermore, after receiving the maintenance instruction, the type of faulty equipment is determined, and the maintenance data of the faulty equipment is feature extracted to obtain the corresponding fault features; faulty equipment maintenance is used as the target word, and a knowledge graph is constructed in advance for faulty equipment maintenance;

[0032] According to the correspondence between the equipment maintenance plan and the fault characteristics, the fault equipment maintenance knowledge graph gives the corresponding maintenance plan for the fault characteristics; after obtaining the maintenance plan, the faulty equipment is maintained with reference to the maintenance plan, and each maintenance information is recorded to construct a maintenance data set.

[0033] Furthermore, the usage and maintenance records of the faulty equipment within the equipment maintenance cycle are obtained, and the maintenance coefficient Hts of the faulty equipment is calculated as follows:

[0034]

[0035] Where n is the number of times the equipment is maintained, Xs(i,j) is the time interval between the i-th maintenance and the j-th maintenance, and Xs a is the average value of the time interval; weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1.

[0036] Furthermore, emergencies within the material management area are monitored, the types of emergencies are characterized and the corresponding type characteristics are obtained; several material and equipment demand plans for handling emergencies are obtained, and a demand plan library is constructed after summarizing them. Based on the correspondence between the type characteristics and the demand plans, the demand plan library matches the corresponding material and equipment demand plans for the emergencies.

[0037] Furthermore, after obtaining the location of each equipment and material in the material and equipment demand plan, its location is used as the target location, and the target location is marked on the electronic map. Combined with the location information of each target location, the path planning algorithm gives a material collection path that connects each target location.

[0038] Furthermore, the trained digital twin model of material collection is obtained, and the material collection path is tested by the digital twin model of material collection, and the obtained collection time is used as the test collection time. Under dimensionless conditions, the method for generating the time coefficient Sts from the test collection time Ct is as follows:

[0039]

[0040] Weight coefficient: 0≤Δ≤1, Ct i is the test collection time of the i-th test, Ct b is the corresponding qualified standard value, and n is the number of tests.

[0041] Furthermore, if the duration coefficient Sts is lower than the preset duration threshold, it is used as the target path and marked on the electronic map; if the duration coefficient Cts is not lower than the duration threshold, the optimization algorithm is used to optimize the current material collection path to obtain the optimized material collection path.

[0042] The property material management system based on the Internet of Things technology includes an alarm information collection unit, which collects alarm information in the material management area and constructs a regional alarm information set, generates an alarm density Mjp from the regional alarm information set, and issues a prompt instruction to the outside if the alarm density Mjp exceeds a density threshold;

[0043] The area allocation unit allocates RFID tags that store relevant information to equipment and materials, monitors and obtains corresponding location information in real time, regards the area where the materials and equipment are located as the storage area, and constrains the location of the storage area;

[0044] The equipment operation monitoring unit collects equipment operation status data through the configured sensor network, and generates the abnormality degree Ypj of the equipment operation from the operation status data. If the abnormality degree Ypj exceeds the abnormal threshold, the fault equipment identification model is used to identify the equipment fault. If there is an operation fault, a fault maintenance instruction is issued to the outside.

[0045] The fault maintenance unit uses the fault equipment maintenance knowledge graph to provide a corresponding maintenance plan for the faulty equipment and record the corresponding maintenance information. The maintenance coefficient Hts of the faulty equipment is generated from the maintenance data of the faulty equipment within the equipment maintenance cycle. If the maintenance coefficient Hts exceeds the frequency threshold, several equally spaced maintenance nodes are set within the equipment maintenance cycle.

[0046] The emergency path planning unit matches the corresponding material and equipment demand plan for the emergency event from the demand plan library, and outputs the material collection path through the path planning algorithm based on the equipment and material data corresponding to the material and equipment demand plan. After verifying the feasibility of the material collection path, it is used as the target path and marked on the electronic map.

[0047] (III) Beneficial effects

[0048] The present invention provides a property material management system and method based on the Internet of Things technology, which has the following beneficial effects:

[0049] 1. Judge whether the alarms in the area are frequent based on the output alarm density Mjp. If the alarm frequency is high, it means that there may be certain hidden dangers in the current area. In actual management, the demand for various materials and equipment may be high, so the corresponding materials and equipment should be prepared and reserved in time.

[0050] 2. After obtaining the relevant information of various materials and equipment, record their locations to avoid loss of equipment and materials and reduce ineffective waste. After obtaining the storage areas of various materials and equipment, constrain and limit several storage areas to make materials and equipment more reasonable and improve efficiency when taking them.

[0051] 3. Generate anomaly degree Ypj from monitoring data, and evaluate whether the operating status of the equipment is abnormal based on the anomaly degree Ypj. If the operating status of the equipment is abnormal, it can be processed in time to ensure the operating status of the equipment.

[0052] 4. Use the trained faulty equipment identification model to identify the equipment's operating faults and determine whether the equipment currently has an operating fault. If an operating fault exists, it can be discovered and maintained in time to enable the equipment to maintain a better operating state.

[0053] 5. The knowledge graph of faulty equipment maintenance provides corresponding maintenance plans for the fault characteristics. When maintaining the fault, targeted maintenance plans can be obtained to achieve targeted maintenance of the faulty equipment and improve the operating status of the faulty equipment.

[0054] 6. Determine whether the equipment is currently maintained frequently based on the maintenance coefficient Hts. If it is frequently maintained, you can set a maintenance cycle containing several maintenance nodes to implement periodic maintenance of the equipment, perform adequate maintenance before the equipment fails, and reduce the risk of equipment failure.

[0055] 7. Monitor abnormal situations and emergencies in the material management area. When an emergency occurs, such as a fire, the demand plan library can match the corresponding material and equipment demand plan for the emergency to avoid temporary selection of corresponding materials. When conducting material management, the speed of emergency response can be accelerated.

[0056] 8. The material collection path is given through the path planning algorithm. When an emergency occurs in the area and a quick response is required, the equipment and materials can be collected and obtained quickly according to the given plan, thereby speeding up the processing efficiency of the emergency.

[0057] 9. Judge whether the current path is feasible based on the time coefficient Sts. If the current path is feasible, the current path can be output. If it is not feasible, it can be re-output or optimized to ensure the feasibility of the material collection path. When an emergency occurs, the materials can be reasonably managed, allocated and dispatched to reduce various risks and hidden dangers and realize the rational use of various materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of the property material management method based on the Internet of Things technology of the present invention;

[0059] Figure 2 This is a structural diagram of a property material management system based on Internet of Things technology of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] See also Figure 1 The present invention provides a property material management method based on Internet of Things technology, including:

[0062] Step 1: Collect alarm information in the material management area and construct a regional alarm information set, generate an alarm density Mjp from the regional alarm information set, and if the alarm density Mjp exceeds the density threshold, issue a prompt instruction to the outside;

[0063] The step 1 includes the following contents:

[0064] Step 101: After selecting the property material management area, monitor the operating status of key equipment such as air conditioners, elevators, and lighting systems. If any abnormality occurs, send an alarm command to the outside. Monitor the safety status of the community through IoT sensors, such as smoke alarms, fire alarms, etc. If any abnormality occurs, send an alarm command to the outside.

[0065] Collect alarm information such as the alarm location and alarm time node when the alarm command is issued to the outside in the material management area within the set observation period, and summarize the acquired alarm information to construct a regional alarm information set;

[0066] Step 102: construct the alarm density Mjp from the alarm information in the regional alarm information set in the following manner:

[0067]

[0068] Where n is the number of alarms issued, L(i,j) is the shortest distance between the i-th alarm area and the j-th alarm area, and L a is the average distance, V(i,j) is the time interval from the i-th alarm to the j-th alarm, V a is the average value of the time interval; weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1; the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0069] Based on historical data and management expectations for the number of alarms, a density threshold is pre-set; if the alarm density Mjp exceeds the density threshold, it means that the current alarms are relatively frequent. If they cannot be processed in time, the risk of subsequent accidents is also high. At this time, a prompt instruction is issued to the outside;

[0070] When used, combine the contents of steps 101 and 102;

[0071] When it is necessary to manage, dispatch and distribute materials in the area, the alarm information in the area is collected first, and the location and corresponding time node when the alarm is issued are obtained, thereby generating the alarm density Mjp in the current stage. Based on the output alarm density Mjp, it is judged whether the alarms in the area are frequent. If the alarm frequency is high, it can be said that there may be certain hidden dangers in the current area. In actual management, the demand for various materials and equipment may be high, so the corresponding materials and equipment should be prepared and reserved in time.

[0072] When alarms are issued frequently in the area involved, the material management area has a greater demand for various materials and equipment. In particular, when emergencies occur in the material management area, such as fire or water intrusion, the existing material management methods can only provide location information of materials and equipment and cannot respond quickly, resulting in the inability to implement emergency response when emergencies actually occur, making it difficult to reduce the risk of accidents caused by emergencies when they occur.

[0073] Step 2: After allocating RFID tags that store relevant information to equipment and materials, real-time monitoring is performed to obtain corresponding location information, and the area where the materials and equipment are located is used as the storage area, and the location of the storage area is constrained;

[0074] The step 2 includes the following contents:

[0075] Step 201: After receiving the prompt instruction, inventory the equipment and materials in the material management area, assign RFID tags to the equipment and materials, and store the relevant information of the materials, such as name, model, purchase date, supplier, usage history, maintenance record, etc.; and combine GPS, Bluetooth beacon or Wi-Fi positioning technology to track the specific location of the materials in real time to ensure that the materials will not be lost or misplaced, and update the location of the equipment and materials in real time;

[0076] Step 202: construct an electronic map covering the material management area, mark the equipment and material pairs in combination with the location data, use the area where the material equipment is located as the storage area, and constrain the location of the storage area. The constraint method is as follows:

[0077]

[0078] Where k is the number of storage areas, Z ij is the shortest distance from the i-th storage area to the j-th storage area, Z a is the average distance, Mjp is the alarm density;

[0079] Select storage areas within the material management area based on constraints and adjust the locations of current materials and equipment;

[0080] When using, combine the contents in steps 201 and 202:

[0081] After obtaining the relevant information of various materials and equipment, recording their location information can avoid the loss of equipment and materials and reduce ineffective waste. At the same time, after obtaining the storage area of ​​each material and equipment, constraining and limiting several storage areas can make the materials and equipment more reasonable and improve efficiency when taking them.

[0082] Step 3: The configured sensor network collects the equipment operation status data, and generates the abnormality degree Ypj of the equipment operation from the operation status data. If the abnormality degree Ypj exceeds the abnormal threshold, the fault equipment identification model is used to identify the equipment fault. If there is an operation fault, a fault maintenance instruction is issued to the outside.

[0083] The step three includes the following contents:

[0084] Step 301: Set up a sensor network on key equipment, including temperature, humidity, pressure, vibration, smoke sensors, etc. The sensor network monitors the operating status and environmental conditions of the equipment, including the operating temperature, humidity and vibration data of the equipment; smoke concentration and voltage and current of the equipment during operation; and aggregate the acquired equipment operating status data to generate an equipment operating data set;

[0085] Step 302: Generate the abnormality degree Ypj of the equipment during operation from the equipment operation status data set, wherein the acquired equipment operation data is linearly normalized and then in the following manner:

[0086]

[0087] Weight coefficient: 0≤F1≤1, 0≤F2≤1 and F2+F1=1; i=1, 2, …, n, where n is the number of monitoring nodes; P i Refers to the equipment operating parameters at the i-th monitoring node, P b is the preset standard value of the equipment operating parameters; Po is the median value of abnormality, Po i is the median value of the abnormality of the operating parameters of the i-th device, Po a is its mean, i=1, 2, …, m, m is the number of equipment operating parameters;

[0088] Based on historical data and management expectations for equipment operation, an abnormal threshold is pre-set; if the abnormality Ypj exceeds the abnormal threshold, it means that the current operating state of the equipment is abnormal and there may be an operating failure. At this time, a fault identification instruction is issued to the outside;

[0089] When in use, after screening out key equipment, the operating status of the equipment is monitored, and the abnormality degree Ypj is generated from the monitoring data. Based on the abnormality degree Ypj, it is evaluated whether the operating status of the equipment is abnormal. If the operating status of the equipment is abnormal, it can be handled in time, thereby ensuring the operating status of the equipment.

[0090] Step 303: After receiving the fault identification instruction, the machine learning algorithm is trained using the sample data to obtain a trained equipment fault identification model, and the current equipment operation data and environmental condition data are used as input to identify the equipment fault using the trained fault equipment identification model;

[0091] If the equipment currently has an operating fault, it will be treated as a faulty device and the corresponding location data will be marked on the electronic map, and a fault maintenance instruction will be issued to the outside;

[0092] When using, combine the contents in steps 301 to 303:

[0093] When there may be abnormalities in the operating status of the equipment, the trained faulty equipment identification model is used to identify the equipment's operating faults based on the collected monitoring data to determine whether the equipment currently has an operating fault. If an operating fault exists, it can be discovered and maintained in time to enable the equipment to maintain a better operating state.

[0094] Step 4: The faulty equipment maintenance knowledge graph provides a corresponding maintenance plan for the faulty equipment and records the corresponding maintenance information. The maintenance coefficient Hts of the faulty equipment is generated from the maintenance data of the faulty equipment within the equipment maintenance cycle. If the maintenance coefficient Hts exceeds the frequency threshold, several equally spaced maintenance nodes are set within the equipment maintenance cycle.

[0095] The step 4 includes the following contents:

[0096] Step 401: After receiving the maintenance instruction, determine the type of faulty equipment, extract features from the maintenance data of the faulty equipment, and obtain corresponding fault features; take faulty equipment maintenance as the target word, and after deep retrieval and entity relationship construction, construct a knowledge graph for faulty equipment maintenance in advance;

[0097] Step 402: using the trained matching model, according to the correspondence between the equipment maintenance plan and the fault characteristics, the fault equipment maintenance knowledge graph provides a corresponding maintenance plan for the fault characteristics; after obtaining the maintenance plan, the faulty equipment is maintained with reference to the maintenance plan, and each maintenance information is recorded, including maintenance time, maintenance personnel, and replaced parts, etc., to construct a maintenance data set;

[0098] When in use, after identifying the equipment's operating failure and obtaining the corresponding failure characteristics, the fault equipment maintenance knowledge graph will give a corresponding maintenance plan for the failure characteristics. When maintaining the failure, targeted maintenance plans can be obtained to achieve targeted maintenance of the faulty equipment and improve the operating status of the faulty equipment.

[0099] Step 403: Set the equipment maintenance cycle, obtain the usage and maintenance records of the faulty equipment within the equipment maintenance cycle, and calculate the maintenance coefficient Hts of the faulty equipment in the following manner:

[0100]

[0101] Where n is the number of times the equipment is maintained, Xs(i,j) is the time interval between the i-th maintenance and the j-th maintenance, and Xs a is the average value of the time interval; weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1; the weight coefficient is consistent with the previous value;

[0102] Based on historical data and the frequency management of fault maintenance, a frequency threshold is pre-set; if the maintenance coefficient exceeds the frequency threshold, it means that the frequency of equipment maintenance is high. At this time, several equally spaced maintenance nodes are set within the equipment maintenance cycle to form periodic maintenance of the equipment;

[0103] When used, combine the contents in steps 401 to 403:

[0104] After maintaining several devices, the maintenance coefficient Hts is generated from the corresponding maintenance records. The maintenance coefficient Hts is used to determine whether the device is currently undergoing frequent maintenance. If it is, a maintenance cycle containing several maintenance nodes can be set to implement periodic maintenance of the equipment. Sufficient maintenance can be performed before the equipment fails, thereby reducing the risk of equipment failure.

[0105] Step 5: The demand plan library matches the corresponding material and equipment demand plan for the emergency event, and the path planning algorithm outputs the material collection path based on the equipment and material data corresponding to the material and equipment demand plan. After verifying the feasibility of the material collection path, it is used as the target path and marked on the electronic map;

[0106] The step five includes the following contents:

[0107] Step 501: monitor emergencies in the material management area, including fire, gas leakage, water intrusion, or wild animal intrusion, etc. After an emergency occurs, identify the type of the emergency and obtain corresponding type features;

[0108] Through online collection or offline formulation, several material and equipment demand plans for handling emergencies are obtained, and a demand plan library is constructed after aggregation. According to the correspondence between type characteristics and demand plans, the demand plan library matches the corresponding material and equipment demand plans for emergencies;

[0109] When in use, when all materials are fully prepared and all equipment is in normal operation, abnormal situations and emergencies in the material management area are monitored. When a situation occurs, such as a fire, the demand plan library matches the corresponding material and equipment demand plan for the emergency, avoiding the temporary selection of corresponding materials. When conducting material management, the speed of emergency response can be accelerated.

[0110] Step 502: After obtaining the locations of each equipment and material in the material and equipment demand plan, the locations are used as target locations, and the target locations are marked on the electronic map. Combined with the location information of each target location, a path planning algorithm is used to provide a material collection path that connects each target location.

[0111] When in use, the location of materials and equipment is obtained, and the material collection path is given through the path planning algorithm after use. When an emergency occurs in the area and a quick response is required, the collection and acquisition of equipment and materials can be completed quickly according to the given plan, thereby speeding up the efficiency of handling emergencies.

[0112] Step 503: construct an initial model using a convolutional neural network, collect sample data, including structural data in the building and data on the existence of materials and equipment, etc., train the initial model using the sample data, obtain a trained digital twin model for material collection, test the material collection path using the digital twin model for material collection, and use the obtained collection time as the test collection duration;

[0113] Under dimensionless conditions, the duration coefficient Sts is generated by the test collection duration Ct, where:

[0114]

[0115] Weight coefficient: 0≤Δ≤1, Ct i is the test collection time of the i-th test, Ct b is the corresponding qualified standard value, n is the number of tests, and the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0116] If the duration coefficient Sts is lower than the preset duration threshold, it is taken as the target path and marked on the electronic map;

[0117] If the duration coefficient Sts is not lower than the duration threshold, an optimization instruction is issued; after receiving the optimization instruction, the optimization algorithm is used to optimize the current material collection path to obtain the optimized material collection path;

[0118] When using, combine the contents in steps 501 to 503:

[0119] After obtaining the material collection path, the material collection digital twin model tests the material collection path, and constructs the corresponding duration coefficient Sts based on the test data. The feasibility of the current path is judged based on the duration coefficient Sts. If the current path is feasible, the current path can be output; if not, it can be re-output or optimized to ensure the feasibility of the material collection path. When an emergency occurs, the materials can be reasonably managed, allocated and dispatched to reduce various risks and hidden dangers and achieve the rational use of various materials.

[0120] The construction method of the knowledge graph for faulty equipment maintenance can refer to the following:

[0121] There are three main methods for constructing knowledge graphs for faulty equipment maintenance: bottom-up, top-down, and a hybrid of the two.

[0122] Bottom-up method: extract entities, attributes and relationships from open linked data sources and add them to the data layer of the knowledge graph. Organize these knowledge elements, gradually abstract them into concepts, and finally form a pattern layer. This method updates quickly and supports the construction of knowledge graphs with large amounts of data, but may face problems such as large knowledge noise and low accuracy.

[0123] Top-down method: Starting from the pre-defined top-level ontology, gradually refine and expand the concepts and relationships to form a well-structured concept hierarchy tree. This method can better reflect the hierarchical relationship between concepts, but it has strong artificial dependence and limited model layer updates. It is suitable for knowledge graph construction with small data volume.

[0124] Hybrid method: combines the advantages of bottom-up and top-down approaches, with strong flexibility, but the model layer is difficult to build.

[0125] Specific construction steps:

[0126] Domain knowledge division: The knowledge in the field of faulty equipment maintenance is divided into different sub-domains, such as equipment domain (topology structure), test domain (data preparation), fault domain (events and disposal), etc. Concepts are abstracted for each sub-domain to form basic components and functional types.

[0127] Data collection and preprocessing: Collect data from various data sources, including semi-structured web pages of encyclopedias, ordinary web pages with a low degree of structure, corpora, and built knowledge bases. Clean, convert, and integrate the collected data to remove irrelevant information such as noise, stop words, and punctuation marks, and perform preprocessing such as word segmentation, part-of-speech tagging, and named entity recognition.

[0128] Knowledge extraction: Entity extraction, automatically discovering specific entities such as names of people, organizations, places, dates, times, etc., also known as named entity learning or named entity recognition. Relationship extraction: using methods and techniques from disciplines such as linguistics, statistics, and information science to discover semantic relationships between entities from text. Attribute extraction: for entities, extracting attribute information related to the entity, such as equipment model, fault type, maintenance record, etc.

[0129] Knowledge fusion: Fusion of knowledge from different data sources to eliminate ambiguity between entities, relationships, attributes and other referents and factual objects. Entity alignment: Determine whether multiple entities in the same or different data sets point to the same entity in the objective world. Attribute value filling: For the case of different values ​​for the same attribute, make decisions based on the number and reliability of data sources to give more accurate attribute values.

[0130] Knowledge processing: abstract concepts from the constructed data layer and construct the model layer of the knowledge graph. Ontology construction: build the top-level ontology from the top-level concepts, and then refine the concepts and relationships to form a well-structured concept hierarchy tree. Quality assessment: conduct a quantitative credibility assessment on the extracted knowledge and retain knowledge with high confidence to ensure the accuracy of the knowledge base.

[0131] Entity learning: Fill the entity matches obtained from knowledge extraction into the constructed pattern layer ontology. Iteratively update the pattern layer: Summarize and summarize based on the new knowledge and data, update the pattern layer, and perform a new round of entity filling based on the updated pattern layer.

[0132] Knowledge update and maintenance, incremental update: based on the updated content published by the knowledge graph data source (such as Wikipedia, etc.), the knowledge graph is partially updated. Complete update: at regular intervals, all data from the knowledge graph data source is extracted and parsed again to ensure the timeliness and accuracy of the knowledge graph.

[0133] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0134] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0135] See also Figure 2 The present invention provides a property material management system based on Internet of Things technology, including:

[0136] The alarm information collection unit collects alarm information in the material management area and constructs a regional alarm information set, generates an alarm density Mjp from the regional alarm information set, and issues a prompt instruction to the outside if the alarm density Mjp exceeds a density threshold;

[0137] The area allocation unit allocates RFID tags that store relevant information to equipment and materials, monitors and obtains corresponding location information in real time, regards the area where the materials and equipment are located as the storage area, and constrains the location of the storage area;

[0138] The equipment operation monitoring unit collects equipment operation status data through the configured sensor network, and generates the abnormality degree Ypj of the equipment operation from the operation status data. If the abnormality degree Ypj exceeds the abnormal threshold, the fault equipment identification model is used to identify the equipment fault. If there is an operation fault, a fault maintenance instruction is issued to the outside.

[0139] The fault maintenance unit uses the fault equipment maintenance knowledge graph to provide a corresponding maintenance plan for the faulty equipment and record the corresponding maintenance information. The maintenance coefficient Hts of the faulty equipment is generated from the maintenance data of the faulty equipment within the equipment maintenance cycle. If the maintenance coefficient Hts exceeds the frequency threshold, several equally spaced maintenance nodes are set within the equipment maintenance cycle.

[0140] The emergency path planning unit matches the corresponding material and equipment demand plan for the emergency event from the demand plan library, and outputs the material collection path through the path planning algorithm based on the equipment and material data corresponding to the material and equipment demand plan. After verifying the feasibility of the material collection path, it is used as the target path and marked on the electronic map.

[0141] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0142] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0143] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0144] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0147] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0148] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A property material management method based on Internet of Things technology, characterized by: include, Collect alarm information in the material management area and construct a regional alarm information set, generate an alarm density Mjp from the regional alarm information set, and if the alarm density Mjp exceeds the density threshold, issue a prompt instruction to the outside; After allocating RFID tags that store relevant information to equipment and materials, real-time monitoring is performed to obtain the corresponding location information, and the area where the equipment and materials are located is used as the storage area, and the location of the storage area is constrained; the method of constraining the location of the storage area is as follows: Where k is the number of storage areas, Z ij is the shortest distance from the i-th storage area to the j-th storage area, Z a is the average distance, Mjp is the alarm density; The configured sensor network collects the equipment operation status data, and generates the abnormality degree Ypj of the equipment operation from the operation status data. If the abnormality degree Ypj exceeds the abnormal threshold, the fault equipment identification model is used to identify the equipment fault. If there is an operation fault, a fault maintenance instruction is issued to the outside. The faulty equipment maintenance knowledge graph provides a corresponding maintenance plan for the faulty equipment and records the corresponding maintenance information. The maintenance coefficient Hts of the faulty equipment is generated from the maintenance data of the faulty equipment within the equipment maintenance cycle. If the maintenance coefficient Hts exceeds the frequency threshold, several equally spaced maintenance nodes are set within the equipment maintenance cycle. The demand plan library matches the corresponding material and equipment demand plan for the emergency, and the path planning algorithm outputs the material collection path based on the equipment and material data corresponding to the material and equipment demand plan. After verifying the feasibility of the material collection path, it is used as the target path and marked on the electronic map.

2. The property material management method based on Internet of Things technology according to claim 1 is characterized in that: After selecting the property material management area, collect the alarm information sent to the outside in the material management area during the observation period, summarize the acquired alarm information to build a regional alarm information set; build the alarm density Mjp from the alarm information in the regional alarm information set, as follows: Where n is the number of alarms issued, L(i,j) is the shortest distance between the i-th alarm area and the j-th alarm area, and L a is the average distance, V(i,j) is the time interval from the i-th alarm to the j-th alarm, V a is the average value of the time interval; weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1.

3. The property material management method based on Internet of Things technology according to claim 2 is characterized in that: After receiving the prompt instruction, the equipment and materials in the material management area are counted, and RFID tags are assigned to the equipment and materials. The RFID tags store the relevant information of the materials and update the location of the equipment and materials in real time; Construct an electronic map covering the material management area, mark equipment and material pairs based on location data, use the area where the materials and equipment are located as the storage area, constrain the location of the storage area, select the storage area within the material management area based on the constraints, and adjust the location of the current materials and equipment.

4. The property material management method based on Internet of Things technology according to claim 3 is characterized in that: A sensor network is set up on the device, the sensor network monitors the operating status and environmental conditions of the device, and the acquired device operating status data is aggregated to generate a device operating data set; The abnormality degree Ypj of the equipment during operation is generated by the equipment operation status data set. If the abnormality degree Ypj exceeds the abnormal threshold, a fault identification instruction is issued to the outside.

5. The property material management method based on Internet of Things technology according to claim 4 is characterized in that: After linear normalization of the acquired equipment operation data, the abnormality degree Ypj of the equipment operation is generated in the following way: Weight coefficient: 0≤F1≤1, 0≤F2≤1 and F2+F1=1; i=1, 2, …, n, where n is the number of monitoring nodes; P i Refers to the equipment operating parameters at the i-th monitoring node, P b It is the preset standard value of the equipment operating parameters; Po is the median value of abnormality, Po i is the median abnormality of the i-th equipment operating parameter, Poa is its mean, i = 1, 2, ..., m, m is the number of equipment operating parameters.

6. The property material management method based on the Internet of Things technology according to claim 5 is characterized in that: After receiving the fault identification instruction, the equipment operation data and environmental condition data are used as input, and the trained faulty equipment identification model is used to identify the equipment fault. If the equipment currently has an operating fault, it will be treated as a faulty device and the corresponding location data will be marked on the electronic map, and a fault maintenance instruction will be issued to the outside.

7. The property material management method based on Internet of Things technology according to claim 6 is characterized in that: After receiving the maintenance instruction, determine the type of faulty equipment and extract features from the maintenance data of the faulty equipment to obtain the corresponding fault features. Take the maintenance of the faulty equipment as the target word and construct a knowledge graph for the maintenance of the faulty equipment in advance. According to the correspondence between the equipment maintenance plan and the fault characteristics, the fault equipment maintenance knowledge graph gives the corresponding maintenance plan for the fault characteristics; after obtaining the maintenance plan, the faulty equipment is maintained with reference to the maintenance plan, and each maintenance information is recorded to construct a maintenance data set.

8. The property material management method based on Internet of Things technology according to claim 7 is characterized in that: Obtain the usage and maintenance records of the faulty equipment within the equipment maintenance cycle, and calculate the maintenance coefficient Hts of the faulty equipment in the following way: Where n is the number of maintenance times of the equipment, Xs(,j) is the time interval between the i-th maintenance and the j-th maintenance, and Xs a is the average value of the time interval; weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1.

9. The property material management method based on Internet of Things technology according to claim 8 is characterized in that: Monitor emergencies in the material management area, identify the types of emergencies, and obtain corresponding type characteristics; Obtain several material and equipment demand plans for handling emergencies, summarize them and build a demand plan library. Based on the correspondence between type characteristics and demand plans, the demand plan library matches the corresponding material and equipment demand plans for emergencies.

10. The property material management method based on Internet of Things technology according to claim 9 is characterized in that: After obtaining the location of each equipment and material in the material and equipment demand plan, its location is used as the target location and marked on the electronic map. Combined with the location information of each target location, the path planning algorithm gives a material collection path that connects each target location.

11. The property material management method based on Internet of Things technology according to claim 10 is characterized in that: Train and acquire the digital twin model for material collection. The digital twin model for material collection will test the material collection path and use the acquired collection time as the test collection duration. Under dimensionless conditions, the method for generating the duration coefficient Sts from the test collection duration Ct is as follows: Weight coefficient: 0≤Δ≤1, Ct i is the test collection time of the i-th test, Ct b is the corresponding qualified standard value, and n is the number of tests.

12. The property material management method based on Internet of Things technology according to claim 11 is characterized in that: If the duration coefficient Sts is lower than the preset duration threshold, it is taken as the target path and marked on the electronic map; If the duration coefficient Sts is not lower than the duration threshold, the optimization algorithm is used to optimize the current material collection path to obtain the optimized material collection path.

13. The property material management system based on Internet of Things technology is characterized by: include, The alarm information collection unit collects alarm information in the material management area and constructs a regional alarm information set, generates an alarm density Mjp from the regional alarm information set, and issues a prompt instruction to the outside if the alarm density Mjp exceeds a density threshold; The area allocation unit allocates RFID tags that store relevant information to equipment and materials, monitors and obtains corresponding location information in real time, regards the area where the materials and equipment are located as the storage area, and constrains the location of the storage area; The equipment operation monitoring unit collects equipment operation status data through the configured sensor network, and generates the abnormality degree Ypj of the equipment operation from the operation status data. If the abnormality degree Ypj exceeds the abnormal threshold, the fault equipment identification model is used to identify the equipment fault. If there is an operation fault, a fault maintenance instruction is issued to the outside. The fault maintenance unit uses the fault equipment maintenance knowledge graph to provide a corresponding maintenance plan for the faulty equipment and record the corresponding maintenance information. The maintenance coefficient Hts of the faulty equipment is generated from the maintenance data of the faulty equipment within the equipment maintenance cycle. If the maintenance coefficient Hts exceeds the frequency threshold, several equally spaced maintenance nodes are set within the equipment maintenance cycle. The emergency path planning unit matches the corresponding material and equipment demand plan for the emergency event from the demand plan library, and outputs the material collection path through the path planning algorithm based on the equipment and material data corresponding to the material and equipment demand plan. After verifying the feasibility of the material collection path, it is used as the target path and marked on the electronic map.

Citation Information

Cited By

  • Intelligent control method and system for waterproof electric heating kettle

    CN119717954A

  • Smart park safety management method and system based on Internet of Things

    CN120278464A