An automatic fault diagnosis and state interaction method, system, device and storage medium based on Internet of Things

Abstract

The application discloses an automatic fault diagnosis and state interaction method, system and device based on Internet of Things and a storage medium, relates to the technical field of industrial Internet of Things and intelligent monitoring, and comprises presenting a unit monitoring page on a display surface, and hierarchically displaying target early warning information entries in a real-time early warning area; in response to a first interaction instruction, switching to an early warning analysis page and synchronously displaying associated early warning, parameter trend and fault analysis results; in response to a second interaction instruction of an early warning trigger logic control, entering a model logic configuration page, automatically positioning and highlighting an early warning trigger link. The method disclosed by the application realizes continuous analysis of target early warning information entries by hierarchical display and page linkage, reduces operation switching, improves source fault positioning efficiency by automatically positioning and highlighting the early warning trigger link, and improves the analysis coherence, positioning accuracy and processing efficiency of fault diagnosis by using early warning shielding rules to suppress invalid interference.

Description

Technical Field

[0001] This invention relates to the field of industrial Internet of Things (IoT) and intelligent monitoring technology, specifically to an IoT-based automatic fault diagnosis and status interaction method, system, device, and storage medium. Background Technology

[0002] With the development of industrial IoT, industrial internet platforms, intelligent monitoring and fault diagnosis technologies, industrial scenarios such as power plants have gradually formed a technical approach based on real-time and historical production data, combined with mechanism analysis, logical rule analysis, big data analysis and artificial intelligence algorithms, to conduct online monitoring, early warning analysis and decision support for equipment operation status. On this basis, related systems can usually realize functions such as unit monitoring, real-time alarm, historical alarm, alarm analysis, model logic construction and knowledge base association, and support trend analysis of alarm-related parameters, location of trigger links, and push of fault causes and countermeasures.

[0003] However, in existing technologies, early warning information display, parameter trend analysis, fault analysis, and model logic tracing are often scattered across different pages or functional modules. After discovering an alarm, operators typically need to switch between the unit monitoring page, alarm analysis page, and model logic page multiple times to gradually obtain the current alarm, historical alarms, parameter change trends, out-of-limit indicators, and fault handling suggestions. This leads to a disconnect between early warning information and analysis basis, difficulty in tracing triggering logic, and secondary alarms easily interfering with the source alarm location, making it difficult to improve fault diagnosis efficiency and interface interaction consistency. Therefore, it is necessary to provide an IoT-based automatic fault diagnosis and status analysis interface interaction solution to achieve linked analysis around target early warning information items, automatic trigger link tracing, and early warning shielding configuration. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that the existing automatic fault diagnosis and status analysis interface interaction methods for equipment have problems such as scattered warning information, parameter trend analysis, fault analysis and trigger logic tracing, cumbersome page switching process, insufficient analysis continuity, difficulty in locating the warning trigger link, secondary warnings easily interfering with the identification of the source warning, and how to achieve warning analysis linkage, automatic tracking of trigger links and warning shielding configuration around the target warning information items.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: an automatic fault diagnosis and status interaction method based on the Internet of Things, comprising: presenting a unit monitoring page on the display surface; when a warning exists for the target unit, displaying the target warning information items hierarchically in the real-time warning area corresponding to the target unit; responding to a first interaction command for the target warning information item on the unit monitoring page, switching the display surface to a warning analysis page, and synchronously displaying the warning information, parameter trends, and fault analysis results associated with the target warning information item on the warning analysis page; responding to a second interaction command for the warning trigger logic control on the warning analysis page, entering the model logic configuration page, automatically locating the warning trigger link corresponding to the target warning information item, and highlighting the warning trigger link.

[0007] As a preferred embodiment of the IoT-based automatic fault diagnosis and status interaction method described in this invention, the unit monitoring page includes: classifying target warning information items into warning levels based on the monitoring model; setting a real-time warning area on the unit monitoring page; writing the warning level into the real-time warning area; assigning corresponding display colors to target warning information items of different warning levels; displaying target warning information items in a hierarchical manner; and pre-configuring warning blocking rules in the monitoring model.

[0008] As a preferred embodiment of the IoT-based automatic fault diagnosis and status interaction method described in this invention, the early warning shielding rule includes: using the output result of the first monitoring model as a prerequisite for the second monitoring model; shielding the early warning of the second monitoring model when the first monitoring model triggers an early warning; establishing an early warning level shielding relationship within the same monitoring model, so that higher-level early warnings shield lower-level early warnings; and introducing hysteresis shielding of RS triggers based on pre-set setting thresholds and reset thresholds to suppress repeated triggering and stopping of the same early warning.

[0009] As a preferred embodiment of the IoT-based automatic fault diagnosis and status interaction method described in this invention, the method of shielding the warning of the second monitoring model includes: establishing a communication connection between the logic output node of the first monitoring model and the logic input node of the second monitoring model; monitoring the output status of the first monitoring model; and when the output status of the first monitoring model is determined to trigger a warning, blocking the warning output path of the second monitoring model in the model logic configuration page to intercept the warning signal of the second monitoring model from being output.

[0010] As a preferred embodiment of the IoT-based automatic fault diagnosis and status interaction method described in this invention, the establishment of the early warning level shielding relationship includes configuring corresponding severity priorities for different over-limit indicators in the logical configuration topology of the same monitoring model. When at least two early warning conditions with different severity priorities are simultaneously met in the same monitoring model, the early warning event with the highest severity priority is extracted and written into the real-time early warning area, and the display commands of early warning events with lower severity priorities are blocked.

[0011] As a preferred embodiment of the IoT-based automatic fault diagnosis and status interaction method described in this invention, the hysteresis shielding introduced by the RS trigger includes: real-time acquisition of time-series data of associated parameter measurement points, and determining the numerical range between the set threshold and the reset threshold as the shielding interval; when the time-series data unidirectionally crosses the set threshold and meets the set condition, the RS trigger is set and triggers an early warning; when the time-series data fluctuates within the shielding interval, the RS trigger is used to maintain the current early warning triggering state; when the time-series data crosses the reset threshold and meets the reset condition, the RS trigger is reset and performs an early warning stop operation.

[0012] As a preferred embodiment of the IoT-based automatic fault diagnosis and status interaction method of the present invention, the automatic location of the target warning information item corresponding to the warning triggering link includes: retrieving the cross-sectional data corresponding to the triggering time of the target warning information item; performing signal backtracking along the logic network in the model logic configuration page; identifying the operation path with the logic state being true as the warning triggering link; performing reverse decoupling calculation on the warning triggering link based on the monitoring model corresponding to the model logic configuration page; separating and obtaining the over-limit indicators that cause the target warning information item to be triggered; retrieving the associated structured fault data based on the over-limit indicators; and outputting the fault analysis results.

[0013] Another objective of this invention is to provide an automatic fault diagnosis and status interaction system based on the Internet of Things, which can solve the problems of fragmented page interaction, difficulty in tracing the warning trigger logic, and low fault analysis efficiency in current automatic fault diagnosis and status interaction technologies by hierarchically displaying target warning information items, performing linkage analysis, and automatically tracing the trigger link.

[0014] As a preferred embodiment of the IoT-based automatic fault diagnosis and status interaction system of the present invention, it includes: a unit monitoring display module, an early warning analysis linkage module, a trigger logic tracing module, and a link highlighting module; the unit monitoring display module is used to present the unit monitoring page on the display surface, and when an early warning exists for the target unit, it displays the target early warning information item in the corresponding real-time early warning area in a hierarchical manner; the early warning analysis linkage module is used to switch the display surface from the unit monitoring page to the early warning analysis page in response to a first interactive command for the target early warning information item, and simultaneously display the early warning information, parameter trends, and fault analysis results associated with the target early warning information item; the trigger logic tracing module is used to enter the model logic configuration page in response to a second interactive command for the early warning trigger logic control in the early warning analysis page, and automatically locate the early warning trigger link corresponding to the target early warning information item; the link highlighting module is used to highlight the early warning trigger link after it is located, so as to facilitate the tracking and analysis of the trigger basis of the target early warning information item.

[0015] Another object of the present invention is to provide an automatic fault diagnosis and status interaction device based on the Internet of Things, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the automatic fault diagnosis and status interaction method based on the Internet of Things.

[0016] Another object of the present invention is to provide an automatic fault diagnosis and status interaction storage medium based on the Internet of Things, wherein a computer program is stored thereon, and when the computer program is executed by a processor, the steps of the automatic fault diagnosis and status interaction method based on the Internet of Things are implemented.

[0017] The beneficial effects of this invention are as follows: The IoT-based automatic fault diagnosis and status interaction method provided by this invention displays target early warning information items hierarchically on the unit monitoring page, and switches to the corresponding early warning analysis page after selecting a target early warning information item, simultaneously displaying early warning information, parameter trends, and fault analysis results. This enables continuous analysis around the same target early warning information item, reducing repeated switching between early warning viewing, trend judgment, and fault analysis. By further entering the model logic configuration page and automatically locating the corresponding early warning triggering link, the traceability of early warning triggering basis and the efficiency of source fault location can be improved. At the same time, by setting early warning blocking rules during the monitoring model configuration stage, secondary early warnings, low-level early warnings, and repeatedly triggered early warnings can be suppressed, reducing the interference of invalid early warnings on the identification and handling of target early warning information items, thereby improving the analysis continuity, location accuracy, and early warning processing efficiency in the automatic fault diagnosis and status interaction process of equipment. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a diagram of the unit monitoring page structure for an automatic fault diagnosis and status interaction method based on the Internet of Things provided in Embodiment 1 of the present invention.

[0020] Figure 2 This is a diagram of the early warning analysis page structure for an automatic fault diagnosis and status interaction method based on the Internet of Things provided in Embodiment 1 of the present invention.

[0021] Figure 3 This is a schematic diagram of the early warning triggering link location for an automatic fault diagnosis and status interaction method based on the Internet of Things provided in Embodiment 1 of the present invention.

[0022] Figure 4 This is a schematic diagram of the hysteresis shielding logic configuration of an RS trigger for an automatic fault diagnosis and status interaction method based on the Internet of Things, provided in Embodiment 1 of the present invention.

[0023] Figure 5 This is a schematic diagram comparing the performance of early warning and blocking rules for an automatic fault diagnosis and status interaction method based on the Internet of Things provided in Embodiment 1 of the present invention. Detailed Implementation

[0024] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0025] Example 1, referring to Figures 1-5 As an embodiment of the present invention, an automatic fault diagnosis and status interaction method based on the Internet of Things is provided, comprising: The unit monitoring panel page 100 is displayed on the display surface M. When there is an early warning for the target unit, the target early warning information item 101a is displayed in a hierarchical manner in the real-time early warning area 101 corresponding to the target unit.

[0026] In response to the first interactive command for the target early warning information item 101a in the unit monitoring page 100, the display screen M will be switched to the early warning analysis page 200, and the early warning information, parameter trends and fault analysis results associated with the target early warning information item 101a will be displayed simultaneously on the early warning analysis page 200.

[0027] In response to the second interactive command for the early warning trigger logic control 201 in the early warning analysis page 200, the system enters the model logic configuration page 300, automatically locates the early warning trigger link corresponding to the target early warning information item 101a, and highlights the early warning trigger link.

[0028] The unit monitoring page 100 includes classifying the target warning information items 101a into warning levels based on the monitoring model. The unit monitoring page 100 also includes a real-time warning area 101, where warning levels are written. Corresponding display colors are assigned to target warning information items 101a at different warning levels, and the target warning information items 101a are displayed in a hierarchical manner, such as... Figure 1 As shown, the monitoring model is pre-configured with early warning blocking rules.

[0029] It should be noted that the unit monitoring page 100 is equipped with a real-time warning area 101, and the warning level definition and warning masking rule configuration for the target warning information item 101a are completed during the monitoring model configuration phase. The target warning information item 101a is divided into three warning levels: Level 1, Level 2, and Level 3. After receiving the target warning information item 101a output by the monitoring model, the unit monitoring page 100 writes the corresponding warning level into the real-time warning area 101 and displays it according to the preset color rules. Specifically, Level 1 warnings are displayed in red, Level 2 warnings are displayed in yellow, and Level 3 warnings are displayed in blue. Level 1 and Level 2 warnings are used to indicate higher priority warnings, while Level 3 warnings are used to indicate lower priority warnings.

[0030] It should also be noted that by pre-defining the warning level of the target warning information items during the configuration phase of the monitoring model, and writing the target warning information items of different levels into the real-time warning area 101 and assigning them corresponding display colors, the unit monitoring page 100 can intuitively distinguish the warning information of different priorities, making it easier for operators to quickly identify high-priority warnings and low-priority warnings.

[0031] It should be noted that when a click operation is performed on target early warning information item 101a, the system responds to the first interactive command for the target early warning information item in the unit monitoring page 100, triggering the display interface jump logic. The display screen M will switch from the unit monitoring page 100 to the early warning analysis page 200 corresponding to the target early warning information item 101a, realizing the linkage switch from global monitoring to in-depth analysis of a single fault. The system retrieves early warning information associated with target early warning information item 101a. This process involves calling the corresponding early warning records, classifying the end status, determining and extracting the current or historical early warning information, and displaying its early warning level and name. Parameter trends are generated, i.e., based on the monitoring model corresponding to target early warning information item 101a, the associated parameter measurement points are determined, time-series data within a preset range before and after the early warning trigger time are retrieved, a multi-parameter trend curve is generated according to a unified time axis, and the trigger time period is interval-marked. The system analyzes the faults by decoupling the early warning triggering link to obtain the out-of-limit indicators, and calls the associated fault phenomena, causes, and countermeasures to generate corresponding fault analysis results. The early warning analysis page 200 displays the early warning information, parameter trends, and fault analysis results simultaneously. By integrating and displaying the above-mentioned associated data and analysis conclusions on the same page, continuous analysis around the target early warning information item 101a is achieved, reducing the operation of operators repeatedly switching between different functional modules, thereby improving the efficiency of fault diagnosis and the continuity of interface interaction.

[0032] The warning masking rules include using the output of the first monitoring model as a prerequisite for the second monitoring model, masking the warning of the second monitoring model when the first monitoring model triggers a warning, establishing a warning level masking relationship within the same monitoring model so that higher-level warnings mask lower-level warnings, and introducing hysteresis masking of the RS trigger 301 based on pre-set set and reset thresholds to suppress repeated triggering and stopping of the same warning, such as... Figure 4 As shown.

[0033] It should be noted that source early warning identification is achieved through cross-model linkage. The output of the first monitoring model is used as a prerequisite for the second monitoring model. Specifically, during the model configuration phase, the output of one model is used as an input condition for other models. When the first monitoring model triggers an early warning, the early warning from the second monitoring model is automatically masked. This avoids multiple secondary alarms from the same fault overwhelming the primary alarm, solving the problem of difficulty in source location caused by the scattered display of early warning information in existing technologies, and ensuring that operators can quickly determine the source of the fault. Secondly, an early warning level masking relationship is established within the same monitoring model, so that higher-level early warnings mask lower-level early warnings. That is, the system will set masking logic within the same model according to the severity, such as a level one early warning suppressing the display of corresponding level two and level three early warnings. In conjunction with the hierarchical display rules of the unit monitoring page 100, corresponding display colors are assigned according to the warning level and written into the real-time warning area 101. Specifically, the first-level warning is displayed in red, the second and third levels are displayed in yellow and blue respectively, thus forming an intuitive visual distinction and highlighting the highest priority risk information. A hysteresis shielding mechanism based on RS trigger 301 is introduced near the warning threshold. The logic characteristics of RS trigger 301 suppress repeated triggering and stopping caused by parameter fluctuations near the threshold. This process uses the set and reset functions of RS trigger 301 to establish a shielding interval near the threshold, preventing the alarm signal from frequently switching between the generation and elimination states due to small fluctuations, thereby improving the stability of the warning state and the continuity of automatic fault diagnosis of the equipment.

[0034] It should also be noted that by achieving source early warning identification through cross-model linkage, the problems of scattered early warning information display and secondary early warnings overshadowing the main alarms are effectively solved, significantly improving the accuracy of operators in determining the source of the fault. By utilizing the level shielding relationship and hierarchical display rules within the same model, intuitive hierarchical levels can be visually formed through color differentiation, thereby optimizing the interactive interface and highlighting the highest priority risk information. A hysteresis shielding mechanism based on RS trigger 301 is introduced near the early warning threshold, and a shielding interval is established using set and reset logic, which effectively suppresses repeated triggering caused by small parameter fluctuations, enhancing the stability of the early warning status and the consistency of diagnosis. By pre-setting rules during the configuration stage, the interference of invalid information on operators is greatly reduced, the operational burden and psychological load are lowered, and the overall processing efficiency of automatic fault diagnosis of equipment is ultimately improved.

[0035] Blocking the warnings of the second monitoring model includes establishing a communication connection between the logic output node of the first monitoring model and the logic input node of the second monitoring model, monitoring the output status of the first monitoring model, and when the output status of the first monitoring model is determined to trigger a warning, blocking the warning output path of the second monitoring model in the model logic configuration page 300, and intercepting the warning signal of the second monitoring model from being output.

[0036] It should be noted that during the monitoring model configuration phase, the system establishes communication connections between models in the topology, configuring the logical output of the first monitoring model as a precondition for the input of the second monitoring model. This means that the output of one model is used as an input condition by other models. The underlying computing components continuously monitor the output status of the first monitoring model. Once the logic determines that the first monitoring model has triggered an alarm, the system cuts off the alarm output path of the second monitoring model in the model logic configuration page 300. In the background, it intercepts and automatically blocks the output of secondary alarm signals from the second monitoring model. In a specific implementation scenario, the NOx average exceeding limit alarm model is set as the first monitoring model as a precondition, and the associated low ammonia injection flow alarm model is set as the second monitoring model. When the actual operating parameters of the unit meet the triggering conditions of the first monitoring model and output an alarm, the system, based on the pre-established communication connections between the logical input and output nodes, triggers a suppression command to intercept and block the output of secondary alarm signals such as low ammonia injection flow caused by the physical reactions of the associated system. By using logical blocking steps, multiple secondary alarm signals generated by the same fault are intercepted at the underlying computation stage, and only the source alarm signal is output and written to the real-time early warning area.

[0037] It should also be noted that by integrating cross-model linkage and same-model level shielding rules, and introducing a hysteresis shielding mechanism based on RS trigger 301, the system effectively overcomes the problems of rampant secondary alarms and frequent false alarms caused by minor parameter fluctuations in complex industrial scenarios. This prevents invalid and redundant information from overwhelming the main source alarms, thereby significantly improving the accuracy of rapid source fault location and the stability of the warning status. At the same time, the system utilizes the dual logic of underlying physical signal cancellation and manual interactive confirmation commands to accurately and dynamically classify the end status of warning records, constructing a rigorous data lifecycle closed loop. This ensures that any abnormal operating condition has achieved physical recovery and is accessible to operators before being automatically archived as historical data. This significantly reduces the information processing load of on-duty personnel while ensuring the security and continuity of intelligent monitoring and operation and maintenance management of all equipment in the plant.

[0038] Establishing a warning level shielding relationship involves configuring corresponding severity priorities for different over-limit indicators in the logical configuration topology of the same monitoring model. When at least two warning conditions with different severity priorities are simultaneously met within the same monitoring model, the warning event with the highest severity priority is extracted and written into the real-time warning area 101, while the display commands for warning events with lower severity priorities are blocked.

[0039] It should be noted that warning judgment nodes are set in the logical configuration topology of the same monitoring model, and corresponding severity priority parameters are assigned to different over-limit indicators. The severity priority parameters are configured with three levels: Level 1 warning, Level 2 warning, and Level 3 warning. During the model operation monitoring phase, the underlying logic operation component continuously acquires and compares real-time data from related parameter measurement points. When the system detects that at least two warning triggering conditions with different severity priorities are met simultaneously within the same monitoring model, the system executes priority filtering logic to logically compare the severity priority parameters of the simultaneously triggered warning events. The system extracts the warning event with the highest severity priority parameter, writes its corresponding information into real-time warning area 101, and generates an interception command at the background logic output node to block the display command sent to the unit monitoring page for warning events with a severity priority lower than the highest. In a specific implementation scenario, for a monitoring model of a certain device, three severity priorities for parameter over-limit are set, with Level 1 warning having the highest priority, Level 2 warning second, and Level 3 warning the lowest. When the real-time time series data of the associated parameter measurement point is abnormal, and the underlying logic operation component of the system determines that the real-time data of the parameter simultaneously meets the triggering conditions of the next level warning and the second level warning of the model, the system extracts the highest priority first level warning event, writes the first level warning into the real-time warning area 101 and displays it with the corresponding red mark, and at the same time intercepts the output and display commands of the second level warning event in the background logic, blocking the display logic of the second level warning on the display interface.

[0040] The hysteresis shielding introduced by the RS trigger 301 includes real-time acquisition of time-series data of the associated parameter measurement points, and the determination of the numerical range between the set threshold and the reset threshold as the shielding interval. When the time-series data unidirectionally crosses the set threshold and meets the set condition, the RS trigger 301 is set and an early warning is triggered. When the time-series data fluctuates within the shielding interval, the RS trigger 301 is used to maintain the current triggering state of the early warning. When the time-series data crosses the reset threshold and meets the reset condition, the RS trigger 301 is reset and an early warning stop operation is performed.

[0041] The performance comparison of the optimized early warning blocking rules compared to the existing single conventional threshold early warning logic is shown in Table 1: Table 1 Performance Comparison Table

[0042] The conventional single-parameter threshold early warning logic listed in Table 1 has a certain ability to detect anomalies compared to other basic alarm methods not listed. However, it still has the defects of a large number of secondary early warnings and a high invalid alarm jitter rate, and cannot meet the real-time requirements of accurate source fault location in complex industrial scenarios.

[0043] The preferred early warning masking rules in this embodiment (covering cross-model pre-emption, same-model level, and RS trigger 301 hysteresis masking) reduce the average number of secondary early warnings by more than 95% and the average root cause location time by more than 86% compared to the existing mainstream early warning logics listed in the table. Furthermore, they reduce the proportion of invalid early warning jitter to below 1%. Compared to other existing early warning logics not listed, the advantages are more significant. They can meet the alarm noise reduction requirements under massive concurrent monitoring points and ensure the accuracy of target early warning trigger link tracing. From the underlying judgment logic level, they provide reliable support for intelligent monitoring and status interaction of all equipment in the plant. Figure 5 As shown.

[0044] It should be noted that the system calls the RS trigger 301 component in the logical configuration topology and reads the pre-configured set threshold and reset threshold parameters. Using the set and reset thresholds as absolute boundaries, a one-dimensional numerical masking interval is established in memory. The timing data of the associated parameter measurement points are acquired in real time and input into a numerical comparator for polling and comparison. When the timing data unidirectionally exceeds the set threshold and meets the preset set condition, the numerical comparator outputs a set pulse to the set terminal (S terminal) of the RS flip-flop 301. The RS flip-flop 301 flips its state and outputs a trigger signal. The system executes an early warning action based on the trigger signal and writes the early warning event into the real-time early warning area. If the timing data experiences a reverse callback and fluctuates within the shielded interval, the RS flip-flop 301 does not respond to the state change of the input terminal and maintains the current trigger output signal. The system keeps the current early warning trigger state and interface display unchanged. Until the timing data completely exceeds the reset threshold and meets the preset reset condition, the system inputs a reset pulse to the reset terminal (R terminal) of the RS flip-flop 301. The RS flip-flop 301 flips its state and outputs a cancellation signal. The system executes an early warning stop operation in the background based on the cancellation signal.

[0045] In a specific implementation scenario, taking a low pressure early warning model for the primary air turbine outlet of a certain unit as an example, the system sets the warning threshold for this parameter to 3.0 kPa and the reset threshold to 3.2 kPa, and establishes the range between 3.0 kPa and 3.2 kPa as the shielded interval. During actual unit operation monitoring, when the real-time acquired primary air turbine outlet pressure time-series data drops to 2.9 kPa (i.e., unidirectionally exceeding the 3.0 kPa threshold), the system determines that the setting condition is met, RS trigger 301 is set, the system triggers a low pressure early warning, and displays it on the unit monitoring panel. After triggering, if the actual pressure fluctuates frequently within the shielded interval of 3.05 kPa to 3.15 kPa due to airflow disturbances, RS trigger 301 remains set, and the system maintains the alarm state and outputs the command unchanged. The system determines that the reset condition is met only when the actual pressure continues to rise to 3.25 kPa (i.e., completely exceeds the reset threshold of 3.2 kPa). The RS trigger 301 is reset and outputs a cancellation signal, and the system then executes the stop and archive operation for the warning.

[0046] The automatic location of the warning triggering link corresponding to the warning information item 101a includes: retrieving the cross-sectional data corresponding to the triggering time of the warning information item 101a; performing signal backtracking along the logic network in the model logic configuration page 300; identifying the operation path with a true logic state as the warning triggering link; performing reverse decoupling calculation on the warning triggering link based on the monitoring model corresponding to the model logic configuration page; separating and obtaining the over-limit indicators that caused the triggering of the warning information item 101a; retrieving the associated structured fault data based on the over-limit indicators; and outputting the fault analysis results.

[0047] It should be noted that during the trigger logic tracing phase, the system calls the underlying time series database to extract the instantaneous values ​​of each associated parameter measurement point that are strictly aligned with the trigger timestamp of the target early warning information entry 101a, and generates static cross-sectional data. The system takes the early warning output node in the model logic configuration page 300 as the starting point and performs a directed graph traversal towards the input node according to the connection relationship of the logic network topology diagram. During the traversal process, the system substitutes the cross-sectional data into each logic operator and comparator, detects and extracts logic branches with true Boolean operation results, and eliminates logic branches with false Boolean operation results. The complete path formed by connecting all logic branches with true operation results is identified as the early warning trigger link. The system performs reverse decoupling calculations along the early warning trigger link, sequentially parses the threshold conditions of the mathematical operation components and judgment components on the link, and restores the logic signal to the data comparison process of the physical measurement points. In this way, the underlying parameters that are currently exceeding the limit are extracted from the many input sources of the model and locked as the over-limit indicators. The system uses the locked over-limit indicators and the identifier of the monitoring model to which they belong as the joint primary key to initiate a query request to the pre-built knowledge base, extracts the corresponding fault phenomena, fault troubleshooting cause list, and standard response measure list, and sends them to the early warning analysis page for display as the fault analysis result.

[0048] In a specific implementation scenario, taking the NOx hourly average exceeding early warning model as an example, when the early warning is triggered, the system extracts the cross-sectional data of each parameter at the moment of triggering. The system traces back from the early warning output node, sequentially passing through the AND gate operator (true), the RS trigger 301 (set), and the signal holding component (true output). Finally, the system highlights the above truth path as the early warning trigger link. The system decouples this link in reverse, identifying the root cause input measurement point leading to the trigger link's conduction as the NOx concentration sensor at the #21 chimney outlet. The instantaneous reading of this sensor (e.g., 33.5 mg / Nm³) exceeding the comparator threshold (30 mg / Nm³) is confirmed as the exceeding indicator. Based on this exceeding indicator, the system searches the knowledge base, retrieves structured fault data, and outputs the corresponding fault phenomenon (NOx concentration increase), fault cause (1. insufficient ammonia supply; 2. non-compliant reactor outlet concentration setting), and countermeasures (checking the ammonia injection valve opening) on ​​the interface.

[0049] It should also be noted that the second interaction command is a click operation, responding to the second interaction command for the warning trigger logic control 201 in the warning analysis page 200, executing a jump from the front-end warning analysis view to the underlying model logic view. In the warning analysis page 200, the system obtains the target warning information item 101a, such as... Figure 2 The system identifies the warning code for Level I NOx hourly average exceeding the standard and retrieves the corresponding monitoring model from the model library.

[0050] When the alarm trigger logic control 201 in the alarm analysis page 200 is clicked, the model logic configuration page 300 is entered, loading the logic configuration topology of the monitoring model. This topology includes input measurement points, such as... Figure 3 The data includes the load of Unit #1, the hourly average NOx value, logic operators, comparators, signal duration timers, R / S triggers, and early warning output nodes.

[0051] After the topology map is loaded, the warning trigger link corresponding to target warning information entry 101a is automatically located. Cross-sectional data corresponding to the target warning trigger time is retrieved, and signal backtracking is performed along the logical network to identify the computation path where the logical state is true. This warning trigger link is highlighted; preferably, active logical nodes and connecting segments are displayed in red, while links that do not meet the trigger conditions remain in their default color.

[0052] On the early warning analysis page 200, the system backend performs reverse decoupling calculations on the early warning triggering link based on the underlying logic chain of the monitoring model, in order to separate and obtain the core over-limit indicators that cause the target early warning information item 101a to be triggered.

[0053] Furthermore, based on the located monitoring model and out-of-limit indicators, the system initiates a query request to the pre-built knowledge base to retrieve fault data strongly correlated with the monitoring model. After the fault data is structured by the system, fault analysis results corresponding to the target warning information item 101a are generated in the fault analysis area of ​​the warning analysis page 200 and displayed synchronously.

[0054] Specifically, the fault analysis results displayed on the interface include the warning number, fault phenomenon, fault cause, and handling measures. The warning number is a unique identification and tracking code automatically generated for the current alarm event, used for data flow and archiving throughout the entire lifecycle. The fault phenomenon displays the system-level abnormal characterization status related to the out-of-limit indicators. The fault cause is listed item by item in the form of operation steps or troubleshooting guidelines, listing the potential physical causes or equipment defects that lead to the fault phenomenon. The handling measures output standardized response strategies and on-site handling guidance for the fault causes.

[0055] It should also be noted that by performing reverse decoupling calculations on the early warning triggering link, the system can accurately extract the core out-of-limit indicators from the complex linkage alarms, breaking through the efficiency bottleneck of tracing the root cause of underlying faults in complex industrial systems. By deeply integrating the decoupled indicators with the knowledge base, the abstract underlying data is transformed into highly structured troubleshooting guidelines and standardized on-site handling strategies. This not only significantly reduces the reliance on the personal experience of operators for fault troubleshooting, but also effectively shortens the emergency response and decision-making time, ensuring the standardization and accuracy of on-site handling actions.

[0056] Example 2, an embodiment of the present invention, provides an automatic fault diagnosis and status interaction system based on the Internet of Things, including a unit monitoring display module, an early warning analysis linkage module, a trigger logic tracing module, and a link highlighting module.

[0057] The unit monitoring display module is used to present the unit monitoring page 100 on the display surface M, and when there is a warning for the target unit, it displays the target warning information item 101a in the corresponding real-time warning area 101 in a hierarchical manner.

[0058] The early warning analysis linkage module is used to respond to the first interactive command for the target early warning information item 101a, switch the display screen M from the unit monitoring page 100 to the early warning analysis page 200, and simultaneously display the early warning information, parameter trends and fault analysis results associated with the target early warning information item 101a.

[0059] The trigger logic tracing module is used to respond to the second interactive command for the warning trigger logic control 201 in the warning analysis page 200, enter the model logic configuration page 300, and automatically locate the warning trigger link corresponding to the target warning information entry 101a.

[0060] The link highlighting module is used to highlight the warning triggering link after it is located, so as to facilitate the tracking and analysis of the triggering basis of the target warning information item 101a.

[0061] This embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements an automatic fault diagnosis and status interaction system based on the Internet of Things as proposed in the above embodiment.

[0062] This embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements an automatic fault diagnosis and status interaction system based on the Internet of Things as proposed in the above embodiment.

[0063] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0064] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0065] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0066] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0067] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An automatic fault diagnosis and status interaction method based on the Internet of Things, characterized in that, include: The unit monitoring page (100) is displayed on the display surface (M). When there is an early warning for the target unit, the target early warning information item (101a) is displayed in a hierarchical manner in the real-time early warning area (101) corresponding to the target unit. In response to the first interactive command for the target early warning information item (101a) in the unit monitoring page (100), the display (M) is switched to the early warning analysis page (200), and the early warning information, parameter trends and fault analysis results associated with the target early warning information item (101a) are displayed synchronously on the early warning analysis page (200); In response to the second interactive command for the warning trigger logic control (201) in the warning analysis page (200), the system enters the model logic configuration page (300) and automatically locates the warning trigger link corresponding to the target warning information item (101a), highlighting the warning trigger link.

2. The automatic fault diagnosis and status interaction method based on the Internet of Things as described in claim 1, characterized in that: The unit monitoring page (100) includes classifying the target early warning information items (101a) into early warning levels based on the monitoring model. The unit monitoring page (100) is set with a real-time early warning area (101). The early warning level is written into the real-time early warning area (101). The target early warning information items (101a) with different early warning levels are assigned corresponding display colors. The target early warning information items (101a) are displayed in a hierarchical manner. The monitoring model is pre-configured with early warning blocking rules.

3. The automatic fault diagnosis and status interaction method based on the Internet of Things as described in claim 2, characterized in that: The warning shielding rules include using the output of the first monitoring model as a prerequisite for the second monitoring model, shielding the warning of the second monitoring model when the first monitoring model triggers a warning, establishing a warning level shielding relationship within the same monitoring model so that higher-level warnings shield lower-level warnings, and introducing hysteresis shielding of the RS trigger (301) based on the preset set threshold and reset threshold to suppress repeated triggering and stopping of the same warning.

4. The automatic fault diagnosis and status interaction method based on the Internet of Things as described in claim 3, characterized in that: The method of shielding the warning of the second monitoring model includes: establishing a communication connection between the logic output node of the first monitoring model and the logic input node of the second monitoring model; monitoring the output status of the first monitoring model; and when it is determined that the output status of the first monitoring model is a warning trigger, blocking the warning output path of the second monitoring model in the model logic configuration page (300) and intercepting the warning signal of the second monitoring model from being output.

5. The automatic fault diagnosis and status interaction method based on the Internet of Things as described in any one of claims 1, 2, and 4, characterized in that: The establishment of the warning level shielding relationship includes configuring corresponding severity priorities for different over-limit indicators in the logical configuration topology of the same monitoring model. When at least two warning conditions with different severity priorities are simultaneously met in the same monitoring model, the warning event with the highest severity priority is extracted and written into the real-time warning area (101), and the display command of the warning event with a lower severity priority is blocked.

6. The automatic fault diagnosis and status interaction method based on the Internet of Things as described in claim 5, characterized in that: The hysteresis shielding introduced by the RS trigger (301) includes: acquiring the time-series data of the associated parameter measurement points in real time, and determining the numerical range between the set threshold and the reset threshold as the shielding interval; when the time-series data unidirectionally crosses the set threshold and meets the set condition, the RS trigger (301) is set and triggers an early warning; when the time-series data fluctuates within the shielding interval, the RS trigger (301) is used to maintain the current early warning triggering state; when the time-series data crosses the reset threshold and meets the reset condition, the RS trigger (301) is reset and performs an early warning stop operation.

7. The automatic fault diagnosis and status interaction method based on the Internet of Things as described in any one of claims 1, 2, 4, and 6, characterized in that: The warning triggering link corresponding to the automatic positioning target warning information item (101a) includes: retrieving the cross-sectional data corresponding to the triggering time of the target warning information item (101a); performing signal backtracking along the logic network in the model logic configuration page (300); identifying the operation path with the logic state being true as the warning triggering link; performing reverse decoupling calculation on the warning triggering link based on the monitoring model corresponding to the model logic configuration page; separating and obtaining the over-limit indicators that cause the target warning information item (101a) to be triggered; retrieving the associated structured fault data based on the over-limit indicators; and outputting the fault analysis results.

8. An automatic fault diagnosis and status interaction system based on the Internet of Things, employing the automatic fault diagnosis and status interaction method based on the Internet of Things as described in any one of claims 1 to 7, characterized in that: This includes a unit monitoring and display module, an early warning analysis and linkage module, a trigger logic tracing module, and a link highlighting module; The unit monitoring display module is used to present the unit monitoring page (100) on the display surface (M), and when there is a warning for the target unit, to display the target warning information item (101a) in the corresponding real-time warning area (101) in a hierarchical manner; The early warning analysis linkage module is used to respond to the first interactive command for the target early warning information item (101a), switch the display screen (M) from the unit monitoring page (100) to the early warning analysis page (200), and simultaneously display the early warning information, parameter trends and fault analysis results associated with the target early warning information item (101a); The trigger logic tracking module is used to respond to the second interactive command for the warning trigger logic control (201) in the warning analysis page (200), enter the model logic configuration page (300), and automatically locate the warning trigger link corresponding to the target warning information item (101a); The link highlighting module is used to highlight the warning triggering link after it is located, so as to facilitate the tracking and analysis of the triggering basis of the target warning information item (101a).

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the automatic fault diagnosis and status interaction method based on the Internet of Things as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the automatic fault diagnosis and status interaction method based on the Internet of Things as described in any one of claims 1 to 7.

Images