Method and device for diagnosing heat supply fault based on topological relation and medium
By applying topological relationship-based fault diagnosis methods in the heating system, the problem of in-depth fault diagnosis in the prior art is solved, and rapid positioning and efficient treatment of heating faults are achieved.
Patent Information
- Application Number
- CN202411621705.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-14
- Publication Date
- 2025-02-18
AI Technical Summary
The existing heating system can only solve isolated problems when it fails and cannot conduct more in-depth fault diagnosis.
Using topological relationship-based method, the first-level user data in the secondary network operation data is extracted through the feedback data provided by the user and converted into a first-level user decision tree. Based on topological relational data, further diagnose whether the abnormal data has a subtree until the fault location is located.
It realizes rapid positioning and in-depth diagnosis of heating faults, saves manpower and time resources, and improves fault handling efficiency.
Smart Images
Figure CN119474101A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of heating fault diagnosis, and in particular to a method, device and medium for diagnosing heating faults based on topological relationships. Background Art
[0002] Various faults may occur during the operation of the heating field, such as pipeline leakage, valve failure, insufficient heat source output, heat exchange station unit failure, etc. Business personnel often need to check a large amount of data to determine the cause of the fault, consuming a lot of manpower and time costs.
[0003] Existing business systems generally lack the use of auxiliary diagnosis programs for heating faults, or when used, they only analyze the problem entity in isolation, and lack analysis of entities related to the problem entity. If the user finds a problem, the existing business system will check the current user's household meter data and room temperature data and make corresponding inferences. It can be foreseen that this inference often cannot provide further fault diagnosis conclusions because it only uses some status data of the current user.
[0004] Through the above analysis, the problems and defects of the prior art are as follows:
[0005] When a problem occurs in a heating system in the prior art, only isolated problems can be solved, and further in-depth fault diagnosis cannot be performed. Summary of the invention
[0006] The embodiments of the present application provide a method, device and medium for diagnosing heating faults based on topological relationships, which can solve the problem that the heating system in the prior art can only solve isolated problems when problems occur and cannot further perform more in-depth fault diagnosis.
[0007] In a first aspect, an embodiment of the present application provides a method for diagnosing heating faults based on topological relationships, the method comprising: extracting primary user data of secondary network operation data based on feedback data provided by the user, and converting the primary user data into a primary user decision tree based on the secondary network topological relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in a cache; calling the secondary network primary warning threshold function, extracting user abnormal data in the primary user decision tree, and checking whether the abnormal data has a subtree; when a subtree is found, extracting secondary user data from the secondary network cache, and converting the secondary user data into a secondary user decision tree based on the secondary network topological relationship data; when a subtree is found in the secondary user decision tree, checking the upstream data and downstream data of the subtree, as well as locating the position of the subtree, the positions of the upstream data and the downstream data, and returning the position of the subtree.
[0008] In one implementation of the present application, before extracting the primary user data in the cache according to the feedback data provided by the user, the method also includes: obtaining secondary network topology relationship data and primary network topology relationship data, wherein the primary network topology relationship data includes the operating data of the primary pipeline, the heat exchange station and the heat source, and the positional relationship of the primary pipeline, the heat exchange station, and the heat source, and the secondary network topology relationship data includes the operating data of the secondary pipeline and the user end, and the positional relationship of the secondary pipeline, the user end and the heat exchange station; exporting the secondary network topology relationship data and the primary network topology relationship data into the form of a dictionary, and storing them in a database, so that the secondary network warning threshold function and the primary network warning threshold function access the database and the cache according to the user position, and the secondary network warning threshold function includes a secondary network first-level warning threshold function and a secondary network second-level warning threshold function.
[0009] In one implementation of the present application, the method also includes: extracting the first-level system data from the primary network operation data, and converting the first-level system data into a first-level system decision tree based on the primary network topology relationship data; calling the primary network warning threshold function, extracting the first-level system abnormal data in the first-level system decision tree, and checking whether the first-level system abnormal data has a subtree; when the subtree is found, extracting the second-level system data from the primary network cache, and converting the second-level system data into a second-level system decision tree based on the primary network topology relationship data; when the subtree is found in the secondary system decision tree, checking the upstream data and downstream data of the subtree, as well as locating the position of the subtree, the position of the upstream data and the downstream data, and returning the position of the subtree.
[0010] In one implementation of the present application, the method also includes: developing microservices for secondary network topology relationship data and primary network topology relationship data based on location information to obtain a microservice module; deploying the microservice module through containerization technology and building in a self-monitoring mechanism.
[0011] In one implementation of the present application, after the microservice module is deployed through containerization technology and a self-monitoring mechanism is built in, the method also includes: reading the secondary network operation data and the primary network operation data to the database and saving them, wherein the operation data of the heat exchange station includes the supply and return water temperature, the supply and return water flow, and the operation load information, and the pipeline includes the primary pipeline and the secondary pipeline; reading the secondary network operation data and the primary network operation data into the cache, and performing incremental updates according to the preset time.
[0012] In one implementation of the present application, a microservice module is deployed through containerization technology, and a self-monitoring mechanism is built in, specifically including: calculating the historical data stored in the database through a machine learning algorithm to obtain abnormal data of the operating data; monitoring the operating data in the cache according to a preset frequency, comparing the current monitoring data with the historical data to check whether there is abnormal data, the abnormal data includes missing operating data, operating data fluctuations greater than a preset threshold, data redundancy and data source mismatch; constructing a secondary network warning threshold function and a primary network warning threshold function according to the abnormal value threshold.
[0013] In one implementation of the present application, after calling the secondary network first-level warning threshold function, extracting user abnormal data in the first-level user decision tree, and checking whether the abnormal data has a subtree, the method also includes: if the subtree is not found, directly returning the location of the user abnormal data.
[0014] In one implementation of the present application, after returning the location of the subtree, the method also includes: providing a visualization interface for the subtree to display the location and path of fault data and abnormal data; configuring interactive functions for the visualization interface, and the interactive functions include zooming, panning, and click highlighting.
[0015] In a second aspect, an embodiment of the present application also provides a device for diagnosing heating faults based on topological relationships, the device comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: extract primary user data of secondary network operation data based on feedback data provided by the user, and convert the primary user data into a primary user decision tree based on the secondary network topological relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in a cache; call the secondary network primary warning threshold function, extract user abnormal data in the primary user decision tree, and check whether the abnormal data has a subtree; when a subtree is found, extract secondary user data from the secondary network cache, and convert the secondary user data into a secondary user decision tree based on the secondary network topological relationship data; when a subtree is found in the secondary user decision tree, check the upstream data and downstream data of the subtree, and locate the position of the subtree, the positions of the upstream data and the downstream data, and return the position of the subtree.
[0016] In a third aspect, an embodiment of the present application also provides a non-volatile computer storage medium for diagnosing heating faults based on topological relationships, storing computer executable instructions, and the computer executable instructions are set to: extract the first-level user data of the secondary network operation data based on the feedback data provided by the user, and convert the first-level user data into a first-level user decision tree based on the secondary network topological relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in the cache; call the secondary network first-level warning threshold function, extract user abnormal data in the first-level user decision tree, and check whether the abnormal data has a subtree; when the subtree is found, extract the second-level user data in the secondary network cache, and convert the second-level user data into a second-level user decision tree based on the secondary network topological relationship data; when the subtree is found in the second-level user decision tree, check the upstream data and downstream data of the subtree, and locate the position of the subtree, the position of the upstream data and the downstream data, and return the position of the subtree.
[0017] The method, device and medium for diagnosing heating faults based on topological relationships provided in the embodiments of the present application can help business personnel automatically analyze a large amount of relevant data, thereby quickly locating faults, helping business personnel to efficiently determine the cause of faults, and saving valuable manpower and time resources. A reasoning method for auxiliary diagnosis of heating faults based on various entity relationships in primary topological relationship data and secondary topological relationship data is proposed, which fills the gap of the lack of auxiliary diagnosis programs for heating faults in existing business systems, or enhances the diagnostic capabilities of auxiliary diagnosis programs for heating faults in existing business systems by analyzing multiple topological relationships. Using the entity topological relationships in the first network and the second network to diagnose heating anomalies is a more comprehensive analysis method, which is more effective than the isolated analysis method of "treating the head for a headache and the foot for a foot pain" used in previous analyses. The physical facts of the upstream and downstream water flows of the first network and the second network pipelines themselves are fully utilized for fault location, which conforms to the principles of thermodynamics. The conclusions drawn from the analysis are more accurate and more convincing. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0019] Figure 1 A flow chart of a method for diagnosing heating failure based on topological relationship provided in an embodiment of the present application;
[0020] Figure 2 A schematic diagram of a heat exchange station failure of a method for diagnosing a heating failure based on a topological relationship provided in an embodiment of the present application;
[0021] Figure 3A schematic diagram of the internal structure of a device for diagnosing heating faults based on topological relationships provided in an embodiment of the present application. DETAILED DESCRIPTION
[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only 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 making creative work are within the scope of protection of the present application.
[0023] The embodiments of the present application provide a method, device and medium for diagnosing heating faults based on topological relationships, which solves the problem that the heating system in the prior art can only solve isolated problems when problems occur and cannot further perform more in-depth fault diagnosis.
[0024] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.
[0025] Figure 1 A flow chart of a method for diagnosing heating failure based on topological relationship provided in an embodiment of the present application. Figure 1 As shown, a method for diagnosing a heating fault based on a topological relationship provided in an embodiment of the present application specifically includes the following steps:
[0026] Step 10: extracting primary user data of secondary network operation data according to feedback data provided by the user, and converting the primary user data into a primary user decision tree based on the secondary network topology relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in the cache;
[0027] It can be understood that in the embodiment of the present application, the heating fault auxiliary diagnosis algorithm mainly covers two application scenarios: user-initiated fault diagnosis scenario; system-initiated fault diagnosis scenario. The reasoning method based on the knowledge graph specifically refers to the reasoning method for auxiliary diagnosis of heating faults based on various entity relationships in the primary network and the secondary network.
[0028] In an embodiment of the present application, the secondary topological relationship data may refer to the pipeline system between the heat exchange station and the end user, and the entities involved may include the heat exchange station, buildings, units, rooms, users, etc.; the primary topological relationship data may refer to the pipeline system between the heat source plant and each heat exchange station, and the entities involved may include the heat source plant, water supply pipeline, return pipeline, heat exchange station, boiler, heat pump, circulation pump, etc.
[0029] That is to say, the fault diagnosis scenario initiated by the user corresponds to the secondary network and the secondary topology relationship data; the fault diagnosis scenario initiated by the system corresponds to the primary network and the primary topology relationship data.
[0030] In this step, for example, the user reports a heating problem in the room to the heating customer service, such as the heater is not hot. After the customer service dispatches, the heating fault auxiliary diagnosis program is started, and the program outputs the auxiliary diagnosis result of the fault and returns it to the customer service.
[0031] In the fault diagnosis scenario initiated by users, the topological relationship in the user topology data is mainly used for fault inference. That is to say, the topological relationship between various entities in the user topology data is used to associate the user entity with several other entities, and further status analysis is performed on these entities, so that the fault diagnosis conclusion can be better extracted.
[0032] For example, the operating status data at the user end includes household meter data and thermometer data. The household meter data includes supply and return water temperature, instantaneous flow rate, and instantaneous heat; the thermometer data includes room temperature; the household meter data and the thermometer data are both stored in a relational database, and a latest record is updated in the cache every 30 seconds. The latest record is the primary user data, which implements the function of initializing the operating status data cache, reads all user operating status data within the current 30 seconds into the cache, and uses the secondary network topology relationship data known in advance to convert the extracted latest record into a decision tree, and starts the background thread to regularly update the cache incrementally to ensure that the latest operating status data of all users is always stored in the cache; as well as supply and return water temperature, supply and return water flow, and operating load information, the latest operating data is also stored in the cache and updated regularly.
[0033] Step 20: Call the first-level warning threshold function of the secondary network, extract the abnormal user data in the first-level user decision tree, and check whether the abnormal data has a subtree;
[0034] In this step, according to the provided user card number, the secondary network first-level warning threshold function is called to query the cache to obtain the metadata and operation status data of the user. In the secondary network first-level warning threshold function, the user operation status data is checked, and a list of abnormal events is extracted. For example, the secondary network first-level warning threshold function is that the temperature meter data is less than 20 degrees, the supply and return water temperature is less than 40 degrees (only for example, depending on the actual situation), etc., and converted into a corresponding inspection state, and a decision tree that meets the state is found. The inspection state is an abstraction of abnormal events. By establishing a decision tree for the inspection state, the core logic of fault diagnosis can be expressed. The decision tree is retrieved according to the obtained inspection state. If there is no subtree with the state as the key value, it means that the state is a terminal state, and it is directly returned to step 301; if there is a subtree with the state as the key value, it means that further diagnosis is needed, that is, the secondary network second-level warning threshold function is called, wherein the metadata of the current user, the decision state subtree, etc. are passed as parameters to the secondary network second-level warning threshold function.
[0035] Step 30: When the subtree is found, extract the secondary user data from the secondary network cache, and convert the secondary user data into a secondary user decision tree based on the secondary network topology relationship data;
[0036] In this step, in the secondary network level 2 warning threshold function, query the cache to obtain the metadata of other users in the unit where the current user is located, and check the running status data of each user in turn. It is also necessary to convert the detected abnormal events into corresponding inspection states. Since there are multiple users, each user corresponds to an inspection state, so it is necessary to count the number of each inspection state, and apply the state merging function to obtain a final state. The decision tree is retrieved using this state. If there is no subtree with this state as the key value, it means that this state is a terminal state, and it is directly returned to step 30'. If there is a subtree with this state as the key value, it means that further diagnosis is required, that is, calling the secondary network level 3 warning threshold function. The metadata of the current user, the decision state subtree, etc. are passed as parameters to the secondary level 3 network warning threshold function.
[0037] That is, in the secondary network third-level warning threshold function, the cache is queried to obtain the metadata of users in other units in the building where the current user is located;
[0038] In the embodiment of the present application, the fourth-level warning threshold function of the secondary network is taken as the final warning threshold function as an example. In actual application, it is determined according to the actual situation. Different judgment branches are entered according to whether the operating data is abnormal, and then the upward analysis is performed step by step according to the room number, unit number, building number, and heat exchange station ID information, that is, whether the status data of the user's related users is also abnormal, and different judgment branches are entered according to whether the status data of the related users is abnormal. Repeat this step, continuously analyze upward, and stop when it finally reaches the heat exchange station level. Not all analysis steps are necessarily terminated at the heat exchange station level, but may be terminated in advance; for example, the room temperature corresponding to a certain user is very low, which is determined to be abnormal heating, but the room temperature of other users in the unit where the user is located is normal, which means that the heating abnormality is only limited to the user's room, and the unit heating is normal. At this time, the upward analysis can be stopped, that is, there is no need to analyze whether other units in the same building have abnormal heating, because the heating abnormality has been locked in the current user's room.
[0039] In this way, if the secondary network level 4 warning threshold function is called, a final conclusion must be returned, the cache will be queried, the metadata of users in other buildings heated by the heat exchange station to which the current user belongs will be obtained, and the operating status data of each user will be checked in turn; if the key value does not exist for this status, the default terminal status will be returned, indicating that the conclusion cannot be diagnosed and the staff needs to be notified.
[0040] Step 40: When a subtree is found in the secondary user decision tree, the upstream data and downstream data of the subtree are checked, and the position of the subtree, the upstream data and the downstream data are located, and the position of the subtree is returned.
[0041] In this step, a diagnostic report is generated based on the returned terminal status and the internal state variables generated during the algorithm operation and returned to the caller.
[0042] As an optional embodiment, before extracting the primary user data in the cache according to the feedback data provided by the user, the method may further include:
[0043] Step 01: Acquire secondary network topology relationship data and primary network topology relationship data, wherein the primary network topology relationship data includes the operation data of the primary pipeline, heat exchange station and heat source, and the position relationship of the primary pipeline, heat exchange station and heat source, and the secondary network topology relationship data includes the operation data of the secondary pipeline and user end, and the position relationship of the secondary pipeline, user end and heat exchange station;
[0044] In this step, secondary network topology relationship data is prepared, which may include, for example, each user's card number, room number, unit number, building number, and the ID of the heat exchange station to which it belongs, as well as each user's household meter data, temperature meter data, heat exchange station operation status data, etc. at each moment.
[0045] Step 02: Export the secondary network topology relationship data and the primary network topology relationship data into a dictionary form and store them in a database, so that the secondary network warning threshold function and the primary network warning threshold function access the database and cache according to the user location. The secondary network warning threshold function includes a secondary network first-level warning threshold function and a secondary network second-level warning threshold function.
[0046] As an optional embodiment, the method may further include:
[0047] Step 10': extract the primary system data from the primary network operation data, and convert the primary system data into a primary system decision tree based on the primary network topology relationship data; Step 20': call the primary network warning threshold function, extract the primary system abnormal data from the primary system decision tree, and check whether the primary system abnormal data has a subtree;
[0048] In this step, the fault diagnosis scenario initiated by the system can refer to the operating status of various entities involved in the primary network and secondary network such as heat source, heat exchange station, heat pump, user meter, etc. monitored by the background system in real time. That is to say, this is a fault diagnosis scenario initiated by the system. When the operating status of one (or some) of the entities is abnormal, the corresponding entity information, such as heat exchange station ID, timestamp, is extracted when an abnormality occurs, and the auxiliary diagnosis program for heating fault is automatically started to help business personnel locate the fault in time. According to the status of the current entity and the status of related entities, enter the corresponding judgment branch, and determine the fault type and location according to the judgment logic of the judgment branch. For example, the current entity is a heat exchange station, and an abnormality is found after detection. Through the upstream and downstream relationship of the pipeline and the position relationship between the heat exchange station and the pipeline, it is inferred which upstream heat exchange stations are the current heat exchange station, and then check the operating status of the upstream heat exchange station, and the operating status of the upstream heat exchange station of the upstream heat exchange station. By analogy, after entering a certain state branch, the final conclusion is inferred from the operating status of each heat exchange station currently obtained.
[0049] It should be noted that the final conclusion depends on the analysis results of each step. For example, starting from a certain heat exchange station, the status detection is abnormal, and it continues to be abnormal when detecting upstream. Finally, the heat source level is detected and the heat source status is found to be abnormal. Based on all the previous detection results, it is inferred that the location of the heating fault is at the heat source.
[0050] In the fault diagnosis scenario initiated by the system, the system topology relationship data is mainly used for fault inference. After fault inference in the user topology relationship data, it may continue to enter the system topology relationship data for fault inference. Therefore, according to the location of the fault inference, it can be divided into a heating fault inference algorithm based on the primary network and a heating fault inference algorithm based on the secondary network.
[0051] It can be understood that in most cases, the algorithms of these two scenarios will not interact with each other, that is, most fault diagnoses will only use one of the algorithms, and they will only interact in a few cases. For example, the fault diagnosis initiated by the user will infer that the problem is in the heat exchange station (a low-probability event), and further use of the primary network topology relationship data, etc., and then use the heat exchange station as the starting point to enter the primary network diagnosis algorithm to see where the problem lies, which is this step.
[0052] Step 30': When a subtree is found, extract the secondary system data from the primary network cache, and convert the secondary system data into a secondary system decision tree based on the primary network topology relationship data; Step 40': When a subtree is found in the secondary system decision tree, check the upstream data and downstream data of the subtree, locate the position of the subtree, the upstream data and the downstream data, and return the position of the subtree.
[0053] The embodiment of the present application uses manually sorted one-network relationship data for illustration, as shown in Table 1. After the one-network relationship data is sorted, it is imported into a graph database for subsequent queries. In this example, the domestic graph database TuGraph can be used as the graph database storage engine.
[0054] Table 1 Primary network topology data
[0055]
[0056] In the actual business system, there are many heat exchange stations and few heat sources, and the heat exchange station is located downstream of the water supply pipeline, so the abnormal heating of the heat exchange station is used as an example for explanation. Extract the heat exchange station information from the detected abnormal event, query the graph database, obtain the heat source to which the heat exchange station belongs, and further query the graph database to obtain the pipeline path from the heat source to the heat exchange station, as well as other heat exchange stations passing on these paths. For related query statements, refer to the graph query statements in the appendix. Check the operating status data of each heat exchange station on the water supply path in turn (from downstream to upstream). When the heating status of a heat exchange station is abnormal, continue to detect its upstream heat exchange station. When the heating status of a heat exchange station is normal, the detection ends.
[0057] like Figure 2As shown, in this example, the heating status of the "Haomen Youyicheng Heat Exchange Station" is abnormal. According to the water supply path, it can be known that its upstream heat exchange station is the "Shanghe Lijing Heat Exchange Station". Then check the heating operation status of this heat exchange station. If the heating status of the "Shanghe Lijing Heat Exchange Station" is also abnormal, then continue to check the operation status of its upstream heat exchange station. When the operation status of a heat exchange station is normal when tracing back, and the operation status of its downstream heat exchange station is abnormal, the abnormality is located. If all heat exchange stations are found to be abnormal when tracing back, the operation status of the heat source can be checked to confirm whether the heat source is abnormal. According to the inspection results of the algorithm, a diagnostic report is generated to explain the location of the abnormality and the possible cause of the failure, and returned to the caller.
[0058] As an optional embodiment, the method may further include: Step 03: developing microservices for the secondary network topology relationship data and the primary network topology relationship data according to the location information to obtain a microservice module;
[0059] In this step, the heating system can be divided into multiple areas according to factors such as geographical location, heating scale, and management needs. The heating topology relationship of each area can be converted into a microservice module, which is responsible for the management of the heating topology relationship in the area and the integration between these modules. When necessary, a suitable data synchronization and update mechanism can be designed to ensure data consistency and real-time performance between different microservice modules.
[0060] Step 04: Deploy microservice modules through containerization technology and build in self-monitoring mechanism.
[0061] As an optional embodiment, the microservice module is deployed through containerization technology, and a self-monitoring mechanism is built in, which may specifically include: Step 041: Calculate the historical data stored in the database through a machine learning algorithm to obtain abnormal data of the operating data; Step 042: Monitor the operating data in the cache according to a preset frequency, compare the current monitoring data with the historical data, and check whether there is abnormal data. The abnormal data includes missing operating data, operating data fluctuations greater than a preset threshold, data redundancy, and data source mismatch; Step 043: Construct a secondary network warning threshold function and a primary network warning threshold function based on the abnormal value threshold.
[0062] In this step, all status data results (abnormal, normal, and abnormal types) are collected, the final fault type and location are summarized, and the abnormal data rules are defined, that is, a certain operating data becomes abnormal when it reaches a certain threshold, as well as the definitions of different abnormal types. The designation of each threshold can be given based on experience or obtained by statistics of historical operating data.
[0063] As an optional embodiment, after deploying the microservice module through containerization technology and building in a self-monitoring mechanism, the method may further include: Step 05: reading the secondary network operation data and the primary network operation data to the database and saving them, wherein the operation data of the heat exchange station includes the supply and return water temperature, the supply and return water flow, and the operation load information, and the pipeline includes the primary pipeline and the secondary pipeline; Step 06: reading the secondary network operation data and the primary network operation data to the cache, and performing incremental updates according to the preset time.
[0064] In this step, since it is necessary to access the status data of the current entity and related entities, and the number of related entities may be large, this causes the fault diagnosis program to require a large number of IO requests, and it is particularly important to speed up the IO request speed. In actual business needs, the entity status data of the current moment is generally requested, and there is no need to request historical data. Therefore, the entity status data of the current moment can be pre-cached, and read directly from the cache when it is needed to avoid reading the database. As time goes by, it is necessary to continuously update the data in the cache to ensure that the latest entity status data is always stored in the cache. In an actual business system, the status data of each entity in the first network and the second network is updated approximately every 30 seconds, so the cache update time can also be set to update every 30 seconds. When querying the database to obtain updated data, you only need to query the incremental updated content without a full update.
[0065] As an optional embodiment, after calling the first-level warning threshold function of the secondary network, extracting user abnormal data in the first-level user decision tree, and checking whether the abnormal data has a subtree, the method may also include: Step 301: If the subtree is not found, directly return the location of the user abnormal data.
[0066] As an optional embodiment, after returning the location of the subtree, the method may also include: Step 50: providing a visualization interface for the subtree to display the location and path of fault data and abnormal data; Step 60: configuring interactive functions for the visualization interface, the interactive functions including zooming, panning, and click highlighting.
[0067] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a device for diagnosing heating failure based on topological relationship, and its structure is as follows: Figure 3 shown.
[0068] Figure 3 A schematic diagram of the internal structure of a device for diagnosing heating failures based on topological relationships provided in an embodiment of the present application. Figure 3 As shown, the device includes:
[0069] at least one processor 301;
[0070] and, a memory 302 communicatively connected to at least one processor;
[0071] The memory 302 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 301 so that the at least one processor 301 can: extract the primary user data of the secondary network operation data according to the feedback data provided by the user, and convert the primary user data into a primary user decision tree based on the secondary network topology relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in the cache; call the secondary network primary warning threshold function, extract the user abnormal data in the primary user decision tree, and check whether the abnormal data has a subtree; when the subtree is found, extract the secondary user data in the secondary network cache, and convert the secondary user data into a secondary user decision tree based on the secondary network topology relationship data; when the subtree is found in the secondary user decision tree, check the upstream data and downstream data of the subtree, and locate the position of the subtree, the positions of the upstream data and the downstream data, and return the position of the subtree.
[0072] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for diagnosing heating faults based on topological relationships stores computer executable instructions, wherein the computer executable instructions are configured to: extract primary user data of secondary network operation data according to feedback data provided by users, and convert the primary user data into a primary user decision tree based on secondary network topological relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in a cache; call a primary warning threshold function of the secondary network, extract abnormal user data from the primary user decision tree, and check whether the abnormal data has a subtree; if a subtree is found, extract secondary user data from the secondary network cache, and convert the secondary user data into a secondary user decision tree based on the secondary network topological relationship data; if a subtree is found in the secondary user decision tree, check the upstream data and downstream data of the subtree, locate the location of the subtree, the location of the upstream data and the downstream data, and return the location of the subtree.
[0073] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0074] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.
[0075] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0076] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0077] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0080] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0081] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0082] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0083] The above is only the embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method for diagnosing heating failure based on topological relationship, characterized in that: The method comprises: Extracting primary user data of secondary network operation data according to feedback data provided by the user, and converting the primary user data into a primary user decision tree based on secondary network topology relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in a cache; Calling the first-level warning threshold function of the secondary network, extracting abnormal user data in the first-level user decision tree, and checking whether the abnormal data has a subtree; In the case where a subtree is found, extracting secondary user data from the secondary network cache, and converting the secondary user data into a secondary user decision tree based on the secondary network topology relationship data; When a subtree is found in the secondary user decision tree, the upstream data and downstream data of the subtree are checked, and the position of the subtree, the upstream data and the downstream data are located, and the position of the subtree is returned.
2. The method for diagnosing heating failure based on topological relationship according to claim 1, characterized in that: Before extracting the primary user data in the cache according to the feedback data provided by the user, the method further includes: Acquire secondary network topology relationship data and primary network topology relationship data, wherein the primary network topology relationship data includes operation data of primary pipelines, heat exchange stations and heat sources, and positional relationships of the primary pipelines, heat exchange stations and heat sources, and the secondary network topology relationship data includes operation data of secondary pipelines and user terminals, and positional relationships of the secondary pipelines, user terminals and heat exchange stations; The secondary network topology relationship data and the primary network topology relationship data are exported into a dictionary form and stored in a database, so that the secondary network warning threshold function and the primary network warning threshold function access the database and cache according to the user location, and the secondary network warning threshold function includes a secondary network first-level warning threshold function and a secondary network second-level warning threshold function.
3. The method for diagnosing heating failure based on topological relationship according to claim 1 is characterized in that: The method further comprises: Extracting primary system data from the primary network operation data, and converting the primary system data into a primary system decision tree based on the primary network topology relationship data; Calling a network alert threshold function once, extracting the first-level system abnormal data in the first-level system decision tree, and checking whether the first-level system abnormal data has a subtree; In the case where a subtree is found, extracting secondary system data from the primary network cache, and converting the secondary system data into a secondary system decision tree based on the primary network topology relationship data; When a subtree is found in the secondary system decision tree, upstream data and downstream data of the subtree are checked, and the position of the subtree, the positions of the upstream data and the downstream data are located, and the position of the subtree is returned.
4. The method for diagnosing heating failure based on topological relationship according to claim 2 is characterized in that: The method further comprises: Performing microservice development on the secondary network topology relationship data and the primary network topology relationship data according to the location information to obtain a microservice module; The microservice module is deployed through containerization technology and has a built-in self-monitoring mechanism.
5. The method for diagnosing heating failure based on topological relationship according to claim 4 is characterized in that: After the microservice module is deployed through containerization technology and a self-monitoring mechanism is built in, the method further includes: Reading the secondary network operation data and the primary network operation data into the database and saving them, wherein the operation data of the heat exchange station includes the supply and return water temperature, the supply and return water flow rate, and the operation load information, and the pipeline includes the primary pipeline and the secondary pipeline; The secondary network operation data and the primary network operation data are read into the cache, and incrementally updated according to a preset time.
6. The method for diagnosing heating failure based on topological relationship according to claim 4 is characterized in that: The microservice modules are deployed through containerization technology and have a built-in self-monitoring mechanism, including: Calculate the historical data stored in the database by a machine learning algorithm to obtain abnormal data of the operating data; Monitor the operating data in the cache according to a preset frequency, compare the current monitoring data with the historical data, and check whether there is abnormal data, the abnormal data includes missing operating data, operating data fluctuation greater than a preset threshold, data redundancy, and data source mismatch; A secondary network warning threshold function and a primary network warning threshold function are constructed according to the abnormal value threshold.
7. The method for diagnosing heating failure based on topological relationship according to claim 1, characterized in that: After calling the primary warning threshold function of the secondary network, extracting abnormal user data in the primary user decision tree, and checking whether the abnormal data has a subtree, the method further includes: If the subtree is not found, the location of the user abnormal data is directly returned.
8. The method for diagnosing heating failure based on topological relationship according to claim 1, characterized in that: After returning the position of the subtree, the method further comprises: Providing a visual interface for the subtree to display the location and path of fault data and abnormal data; Interactive functions are configured for the visualization interface, and the interactive functions include zooming, panning, and clicking and highlighting.
9. A device for diagnosing heating failure based on topological relationship, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Extracting primary user data of secondary network operation data according to feedback data provided by the user, and converting the primary user data into a primary user decision tree based on secondary network topology relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in a cache; Calling the first-level warning threshold function of the secondary network, extracting abnormal user data in the first-level user decision tree, and checking whether the abnormal data has a subtree; In the case where a subtree is found, extracting secondary user data from the secondary network cache, and converting the secondary user data into a secondary user decision tree based on the secondary network topology relationship data; When a subtree is found in the secondary user decision tree, the upstream data and downstream data of the subtree are checked, and the position of the subtree, the upstream data and the downstream data are located, and the position of the subtree is returned.
10. A non-volatile computer storage medium for diagnosing heating faults based on topological relationships, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Extracting primary user data of secondary network operation data according to feedback data provided by the user, and converting the primary user data into a primary user decision tree based on secondary network topology relationship data, wherein the feedback data includes location information and fault data, and the operation data is located in a cache; Calling the first-level warning threshold function of the secondary network, extracting abnormal user data in the first-level user decision tree, and checking whether the abnormal data has a subtree; In the case where a subtree is found, extracting secondary user data from the secondary network cache, and converting the secondary user data into a secondary user decision tree based on the secondary network topology relationship data; When a subtree is found in the secondary user decision tree, the upstream data and downstream data of the subtree are checked, and the position of the subtree, the upstream data and the downstream data are located, and the position of the subtree is returned.