A method and system for intelligent multi-point monitoring of a genset

Abstract

The present application relates to the technical field of power generation equipment monitoring, and particularly relates to a generator set intelligent multi-point monitoring method and system; the method comprises the following steps: obtaining generator set data, dividing the generator set into first-level and second-level monitoring sub-regions; deploying multiple types of sensors according to the monitoring requirements of key components of each monitoring sub-region, and collecting multi-dimensional parameters of the sub-region in real time; analyzing the multi-dimensional parameters of the sub-region in real time according to the multi-dimensional parameters, identifying abnormal conditions of power generation and grid connection, and performing multi-level warning and abnormal positioning; the system comprises the following modules: a multi-point region division module, a multi-dimensional data monitoring module and a power generation and grid connection abnormal warning module; through the above-mentioned mode, the abnormal identification efficiency and adaptability are improved, so as to improve the safety and grid connection reliability of the generator set operation.

Description

Technical Field

[0001] This invention relates to the field of power generation equipment monitoring technology, and in particular to an intelligent multi-point monitoring method and system for generator sets. Background Technology

[0002] With the large-scale development of power systems, generator sets, as core equipment for power supply, directly affect grid security and power supply reliability through their operational stability. Currently, generator set monitoring mainly relies on traditional single-point or localized area monitoring methods, which have the following technical shortcomings:

[0003] Existing technologies mostly adopt a unified monitoring mode, without classifying and dividing the components according to their functional importance. This leads to an imbalance in the allocation of monitoring resources between core and auxiliary components, making it difficult to adapt to the differentiated monitoring needs of the complex structure of the unit, resulting in low efficiency and poor adaptability in anomaly identification.

[0004] Therefore, it is essential to propose an intelligent multi-point monitoring method and system for generator sets that improves the efficiency and adaptability of anomaly identification. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent multi-point monitoring method and system for generator sets, aiming to solve the technical problems of low efficiency and poor adaptability in the existing generator set monitoring anomaly identification.

[0006] To achieve the above objectives, the present invention employs an intelligent multi-point monitoring method for generator sets, comprising the following steps:

[0007] Acquire generator set data and divide the generator set into primary and secondary monitoring sub-areas;

[0008] Based on the monitoring needs of key components in each monitoring sub-area, multiple types of sensors are deployed to collect multi-dimensional parameters of the sub-area in real time.

[0009] Based on real-time analysis of multi-dimensional parameters in sub-regions, abnormal power generation and grid connection situations are identified, and multi-level warnings and anomaly location are provided.

[0010] In the steps of acquiring generator set data and dividing the generator set into primary and secondary monitoring sub-areas:

[0011] Collect the overall structural parameters, operating characteristic data and historical monitoring records of the generator set, and delineate the distribution range of the core area and auxiliary area of ​​the generator set;

[0012] The core area is designated as a first-level monitoring sub-area, and the auxiliary area is designated as a second-level monitoring sub-area.

[0013] After the steps of designating the core area as a primary monitoring sub-area and the auxiliary area as a secondary monitoring sub-area:

[0014] Establish a sub-region boundary identifier and association table to determine the spatial connection and data interaction interface between the first-level and second-level sub-regions.

[0015] In the process of designating the core area as a primary monitoring sub-area and the auxiliary area as a secondary monitoring sub-area:

[0016] Based on real-time monitoring of unit operation, key component modifications, and historical fault statistics, the first-level and second-level sub-regions are dynamically adjusted.

[0017] If a secondary sub-region is upgraded to a core functional support point, its functional weight will be increased; if some devices in a primary sub-region are converted to backup devices, their functional weight will be reduced.

[0018] Among these steps, the dynamic adjustment of primary and secondary sub-regions is based on real-time monitoring of unit operation, key component modifications, and historical fault statistics:

[0019] Based on the recalculated functional weights, adjust the boundaries and levels of sub-regions:

[0020] Update the sub-region association table and adjust the interface rules between the first-level and second-level sub-regions.

[0021] Among them, the step of deploying multiple types of sensors to collect multi-dimensional parameters of the sub-areas in real time, based on the monitoring needs of key components in each monitoring sub-area:

[0022] Analyze the operating characteristics of key components in the first-level sub-region and determine the types of parameters to be monitored, including temperature, vibration, voltage, current, and rotational speed.

[0023] For key components in the secondary sub-region, determine the types of parameters to be monitored, including pressure, flow rate, liquid level, and operating status signals;

[0024] Based on the required accuracy of parameter monitoring and the characteristics of the sub-regional environment, select the sensor type and deploy the sensor points.

[0025] After selecting the sensor type and deploying the sensors based on the required parameter monitoring accuracy and the characteristics of the sub-regional environment:

[0026] Configure the sensor acquisition frequency, acquire multi-dimensional parameters, and perform preliminary preprocessing on the multi-dimensional parameters.

[0027] Among them, the steps of analyzing multi-dimensional parameters of sub-regions in real time based on multi-dimensional parameters, identifying abnormal power generation and grid connection situations, and performing multi-level warnings and anomaly location are as follows:

[0028] Construct a normal operation threshold model for core parameters in the first-level sub-region and a correlation model for auxiliary parameters in the second-level sub-region;

[0029] The multi-dimensional parameters collected in real time are compared and analyzed with the corresponding model, and anomaly identification requests are triggered based on the analysis results.

[0030] Warning levels are classified according to the importance and scope of impact of abnormal parameters, and multiple levels of warnings are issued.

[0031] Based on the sub-region division information and sensor deployment locations, the faulty component is located, and a location report containing the trend of abnormal parameter changes and the status of related components is generated.

[0032] Among them, in the step of comparing and analyzing the multi-dimensional parameters collected in real time with the corresponding model, and triggering an anomaly identification request based on the analysis results:

[0033] An anomaly detection request is triggered when the analysis results show that either the parameters of the first-level sub-region exceed the threshold or the correlation between the parameters of the second-level sub-region is abnormal.

[0034] This invention also provides an intelligent multi-point monitoring system for generator sets, including a multi-point area division module, a multi-dimensional data monitoring module, and a power generation and grid connection anomaly warning module; wherein:

[0035] The multi-point area division module is used to acquire generator set data and divide the generator set into primary and secondary monitoring sub-areas.

[0036] The multi-dimensional data monitoring module is used to deploy multiple types of sensors to collect multi-dimensional parameters of the sub-area in real time, based on the monitoring needs of key components in each monitoring sub-area.

[0037] The power generation and grid connection anomaly warning module is used to analyze multi-dimensional parameters of sub-regions in real time based on multi-dimensional parameters, identify abnormal power generation and grid connection situations, and perform multi-level warnings and anomaly location.

[0038] This invention discloses an intelligent multi-point monitoring method and system for generator sets, which employs a multi-point area division module, a multi-dimensional data monitoring module, and a power generation and grid connection anomaly warning module to perform the following steps: acquiring generator set data and dividing the generator set into primary and secondary monitoring sub-regions; deploying multiple types of sensors according to the monitoring requirements of key components in each monitoring sub-region to collect multi-dimensional parameters of the sub-region in real time; analyzing the multi-dimensional parameters of the sub-region in real time based on the multi-dimensional parameters, identifying power generation and grid connection anomalies, and performing multi-level warnings and anomaly location; through the above methods, improving the efficiency and adaptability of anomaly identification, thereby enhancing the safety of generator set operation and grid connection reliability. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. 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.

[0040] Figure 1 This is a flowchart of the steps of the intelligent multi-point monitoring method for generator sets of the present invention.

[0041] Figure 2 This is a flowchart of steps S100 of the present invention.

[0042] Figure 3 This is a flowchart of steps S200 of the present invention.

[0043] Figure 4 This is a flowchart of steps S300 of the present invention.

[0044] Figure 5 This is a schematic diagram of the intelligent multi-point monitoring system for generator sets of the present invention.

[0045] Figure 6 This is a schematic diagram of the electronic device of the present invention.

[0046] 401 - Multi-point area division module, 402 - Multi-dimensional data monitoring module, 403 - Power generation and grid connection anomaly warning module. Detailed Implementation

[0047] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0048] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0049] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0050] Please see Figures 1-4 This invention provides a method for intelligent multi-point monitoring of generator sets, comprising the following steps:

[0051] S100: Acquire generator set data and divide the generator set into primary and secondary monitoring sub-areas.

[0052] In this embodiment, generator set data is acquired, and the generator set is divided into primary and secondary monitoring sub-regions. The specific process is as follows:

[0053] S101: Collect the overall structural parameters, operating characteristic data and historical monitoring records of the generator set, and delineate the distribution range of the core area and auxiliary area of ​​the generator set;

[0054] S102: Designate the core area as a first-level monitoring sub-area and the auxiliary area as a second-level monitoring sub-area;

[0055] S103: Establish sub-region boundary identifiers and association tables, and determine the spatial connection and data interaction interface between the first-level and second-level sub-regions.

[0056] Furthermore, in the steps of designating the core area as a primary monitoring sub-area and the auxiliary area as a secondary monitoring sub-area:

[0057] Based on real-time monitoring of unit operation, key component modifications, and historical fault statistics, the first-level and second-level sub-regions are dynamically adjusted.

[0058] If a secondary sub-region is upgraded to a core functional support point, its functional weight will be increased; if some equipment in a primary sub-region is converted to backup equipment, its functional weight will be decreased. The functional weight is calculated by weighting the component criticality score (0~10 points) and the historical failure rate (times / year), and the weight adjustment threshold is set at ±20%. The sub-region boundary is adjusted when the change in functional weight exceeds the threshold, and the boundary movement range shall not exceed 15% of the original region.

[0059] Based on the recalculated functional weights, adjust the boundaries and levels of sub-regions:

[0060] Update the sub-region association table and adjust the interface rules between the first-level and second-level sub-regions.

[0061] In the above process, the overall structural parameters of the generator set (such as the size of each system and the connection method of components), operating characteristic data (such as rated power, speed range, grid connection response time) and historical monitoring records (including past fault locations, frequencies and impact ranges) are collected first. Based on these data, the physical distribution range of the core area of ​​the generator set (key systems that directly participate in power generation and grid connection, such as the generator body, main excitation system, grid connection control cabinet, etc.) and the auxiliary area (supporting systems that support the operation of the core area, such as fuel supply system, cooling circulation system, ventilation device, etc.) is determined.

[0062] Based on the importance of regional functions, the core area is designated as a first-level monitoring sub-area (which requires key monitoring to ensure grid connection stability), and the auxiliary area is designated as a second-level monitoring sub-area (which is monitored to support the normal operation of the core functions).

[0063] Clear boundary markers are set for each sub-region (e.g., defined by spatial coordinates or component relationships), and a sub-region relationship table is established to record in detail the spatial connection positions between primary and secondary sub-regions (e.g., the connection interface between the cooling system and the generator) and data interaction interfaces (e.g., the type and path of status signals transmitted from the auxiliary region to the core region). The sub-region relationship table includes the following fields: sub-region ID, boundary coordinates, associated sub-region ID, data interaction interface type (e.g., CAN bus, Ethernet), and interaction frequency (times / second). Example: Primary sub-region A (coordinates X1-Y1-Z1) interacts with secondary sub-region B (coordinates X2-Y2-Z2) via CAN bus at a frequency of 10 times / second.

[0064] Furthermore, the sub-region level can be dynamically adjusted. Specifically, this is achieved through real-time monitoring of unit operation modes (such as grid-connected / off-grid switching, significant load fluctuations), key component upgrades (such as adding energy storage modules, replacing intelligent speed control systems), and historical fault statistics (such as frequent faults in a certain auxiliary area affecting core functions). When any of these situations occur, the adjustment mechanism is activated. If a former secondary sub-region becomes a direct support point for core functions due to functional upgrades (such as newly added frequency regulation auxiliary devices needing to participate in grid-connected frequency regulation in real time), its functional weight is increased. If some equipment in a former primary sub-region is switched to standby mode (such as standby generators being in standby mode for extended periods), its functional weight is decreased. Based on the recalculated functional weights, the sub-region division boundaries (such as expanding the monitoring range of upgraded areas) and levels (such as upgrading high-weight auxiliary areas to primary level and downgrading low-weight core areas to secondary level) are adjusted. Simultaneously, the sub-region association table is updated, and the interface rules for data interaction frequency and linkage control logic between the adjusted primary and secondary sub-regions are redefined.

[0065] S200: Based on the monitoring needs of key components in each monitoring sub-area, deploy multiple types of sensors to collect multi-dimensional parameters of the sub-area in real time.

[0066] In this embodiment, multiple types of sensors are deployed according to the monitoring requirements of key components in each monitored sub-area to collect multi-dimensional parameters of the sub-area in real time. The specific process is as follows:

[0067] S201: Analyze the operating characteristics of key components in the first-level sub-region and determine the types of parameters to be monitored, including temperature, vibration, voltage, current, and rotational speed;

[0068] S202: For key components in the secondary sub-region, determine the types of parameters to be monitored, including pressure, flow rate, liquid level, and operating status signals;

[0069] S203: Select the sensor type and deploy the sensor locations based on the parameter monitoring accuracy requirements and the environmental characteristics of the sub-area;

[0070] S204: Configure the sensor acquisition frequency, acquire multi-dimensional parameters, and perform preliminary preprocessing on the multi-dimensional parameters.

[0071] In the above process, for the key components of the first-level sub-region (such as generator stator, rotor, main circuit breaker, etc.), their operating characteristics (such as high-speed rotation, high voltage output, strong electromagnetic environment, etc.) are analyzed to determine the types of core parameters that need to be monitored, including temperature (winding temperature, bearing temperature), vibration (radial vibration, axial displacement), voltage (stator voltage, excitation voltage), current (stator current, excitation current), speed (rotor speed), etc.

[0072] For key components in the secondary sub-region (such as fuel pumps, coolant pumps, fuel tanks, filters, etc.), determine the types of auxiliary parameters that need to be monitored, including pressure (fuel pressure, coolant pressure), flow rate (fuel flow rate, coolant flow rate), liquid level (fuel tank level, coolant level), and operating status signals (equipment start / stop status, valve open / close status), etc.

[0073] Based on the parameter monitoring accuracy requirements (e.g., the temperature measurement accuracy of the first-level sub-region needs to reach ±1℃, and the pressure measurement accuracy of the second-level sub-region needs to reach ±0.05MPa) and the environmental characteristics of the sub-region (e.g., high temperature, humidity, strong electromagnetic interference, dust, etc.), select appropriate sensor types (e.g., thermocouples for high temperature measurement, piezoelectric vibration sensors for vibration monitoring, Hall effect sensors for current measurement, ultrasonic sensors for liquid level detection, etc.), and deploy the sensors at locations that avoid interference from component movement and ensure unobstructed signal transmission.

[0074] Configure the sensor acquisition frequency: set the acquisition frequency of the first-level sub-region to 10~50Hz and the second-level sub-region to 1~10Hz), acquire multi-dimensional parameters in real time, and perform preliminary preprocessing on the data (such as removing obvious outliers, standardizing the data format, and adding timestamps).

[0075] S300: Based on multi-dimensional parameters, analyze the multi-dimensional parameters of the sub-region in real time, identify abnormal power generation and grid connection situations, and provide multi-level warnings and anomaly location.

[0076] In this embodiment, multi-dimensional parameters of a sub-region are analyzed in real time based on multi-dimensional parameters to identify abnormal power generation and grid connection situations, and multi-level warnings and anomaly location are performed. The specific process is as follows:

[0077] S301: Construct a normal operation threshold model for core parameters of the first-level sub-region and a correlation model for auxiliary parameters of the second-level sub-region;

[0078] S302: Compare and analyze the multi-dimensional parameters collected in real time with the corresponding model. Based on the analysis results, if the analysis results show that the parameters of the first-level sub-region exceed the threshold or the correlation of the parameters of the second-level sub-region is abnormal, an anomaly identification request will be triggered.

[0079] S303: Classify warning levels according to the importance and scope of impact of abnormal parameters, and issue multi-level warnings;

[0080] S304: Based on the sub-region division information and sensor deployment locations, locate the faulty component and generate a location report that includes the trend of abnormal parameter changes and the status of related components.

[0081] In the above process, based on the generator set design standards and historical normal operation data, a normal operation threshold model for the core parameters of the first-level sub-region is constructed (such as voltage stability range of 380±5V, frequency stability range of 50±0.2Hz, stator temperature upper limit of 120℃, etc.). At the same time, a correlation model for auxiliary parameters of the second-level sub-region is constructed (such as the linear relationship between fuel pressure and speed, the corresponding curve of cooling water temperature and unit load, etc.). The correlation model for auxiliary parameters of the second-level sub-region adopts the linear regression algorithm. For example, the relationship between fuel pressure (P) and speed (N) is P=0.5N+2 (unit: MPa / rpm); the relationship between cooling water temperature (T) and load (L) is T=0.2L+30 (unit: ℃ / kW).

[0082] The normal operation threshold model for core parameters in the first-level sub-region is used to define the normal fluctuation range of parameters that directly affect the core functions of power generation and grid connection (such as voltage, current, temperature, and speed). The specific construction process is as follows:

[0083] Parameter sample collection and screening involves gathering historical parameter data for key components (such as generator stators, main circuit breakers, and excitation systems) in the primary sub-regions under typical operating scenarios, including rated conditions, load fluctuations (50%~100% rated load), and start-up / shutdown. The time span should cover at least three complete operating cycles (e.g., three months of continuous operating data). Abnormal data caused by known faults or maintenance operations are removed, and valid samples under normal operating conditions are retained to form the original dataset.

[0084] Parameter distribution characteristic analysis involves statistical analysis of the filtered dataset:

[0085] Calculate the mean, standard deviation, maximum, minimum and 95% confidence interval of each core parameter (such as stator temperature, grid voltage and rotor speed);

[0086] Analyze the variation patterns of parameters with operating conditions (such as the linear relationship between speed and load increase, and the cumulative trend of temperature with operating time) to identify the stable fluctuation range of parameters under different scenarios.

[0087] The threshold range is determined by combining generator set design standards (such as parameter ratings provided by the manufacturer and industry safety regulations) and statistical analysis results to determine the threshold range for each core parameter:

[0088] For parameters that require strict stability, such as voltage and frequency, take ±5% of the design rated value as the threshold (e.g., when the rated voltage is 380V, the threshold is set to 361V~399V).

[0089] For parameters related to operating time, such as temperature and vibration, set dynamic thresholds (e.g., the stator temperature threshold is ≤80℃ during the startup phase and ≤120℃ during the continuous operation phase).

[0090] For sudden fluctuation parameters (such as short-circuit current), set an upper limit threshold with reference to historical fault critical values ​​(such as instantaneous current not exceeding 10 times the rated current).

[0091] Model validation and optimization utilize newly collected normal operation data to verify the effectiveness of the threshold model. If over 99% of the normal data falls within the threshold range, the model is initially effective. If a significant number of normal data points are misclassified as abnormal, the statistical sample or threshold range needs to be readjusted. Simultaneously, historical failure cases are used to ensure that the parameter values ​​at the time of failure all exceed the threshold range, ultimately forming a stable threshold model.

[0092] The secondary sub-region auxiliary parameter correlation model is used to describe the linkage relationship between auxiliary system parameters (such as pressure, flow rate, and liquid level) and with core parameters (such as the matching relationship between fuel pressure and speed). The specific construction process is as follows:

[0093] Correlation parameters are used to identify and analyze the operational logic of key components (such as fuel systems and cooling systems) in secondary sub-regions, determining parameter pairs with interrelationships. For example:

[0094] In the fuel system, "fuel pressure" is related to "engine speed" and "fuel flow".

[0095] In the cooling system, "cooling water temperature" is related to "unit load" and "cooling fan speed";

[0096] The relationship between auxiliary and core areas, such as the relationship between "lubricating oil pressure" and "generator speed".

[0097] The correlation data modeling process collects the above parameters from synchronously collected data under normal operating conditions (ensuring consistent timestamps), and constructs a correlation model through data fitting and machine learning algorithms:

[0098] For linearly correlated parameters (such as fuel flow increasing linearly with engine speed), a linear regression model is used to determine the correlation coefficients such as the slope and intercept between the parameters.

[0099] For nonlinear correlation parameters (such as cooling water temperature rising slowly first and then rapidly with increasing load), multinomial regression or decision tree models are used to fit the nonlinear curve of parameter change.

[0100] For discrete state associations (such as the on / off relationship between "valve on / off state" and "pipeline pressure"), establish a state mapping table (e.g., the pressure should be ≥0.5MPa when the valve is fully open and ≤0.1MPa when it is closed).

[0101] The correlation deviation threshold is set to calculate the range of deviation between the actual parameter values ​​and the model predictions during normal operation. Deviations within the 95% confidence interval are defined as normal fluctuations, while deviations exceeding this range are considered abnormal correlations. For example:

[0102] In the correlation model between fuel pressure and engine speed, if the model predicts a pressure of 0.8 MPa and the actual pressure deviates from the predicted value by more than ±0.1 MPa, it is considered abnormal.

[0103] In the correlation model between cooling water temperature and load, if the actual water temperature is more than 5°C higher than the model's predicted value, it is considered abnormal.

[0104] Dynamic model calibration updates model parameters periodically (e.g., monthly) with new operational data to adapt to drift in correlations caused by equipment aging and environmental changes (such as the impact of seasonal temperature variations on the cooling system). When components are replaced in secondary sub-regions (e.g., fuel pump replacement), data is re-acquired and the correlation model is calibrated to ensure the accuracy of correlations.

[0105] The multi-dimensional parameters, collected and preprocessed in real time, are dynamically compared and analyzed with the corresponding model. When the parameters of the first-level sub-region exceed the threshold model range (such as a sudden voltage surge to 420V), or the parameters of the second-level sub-region deviate from the correlation model pattern (such as a sudden drop in fuel pressure when the engine speed remains constant), an anomaly identification request is triggered.

[0106] Warning levels are categorized based on the importance and scope of the abnormal parameters: Level 1 warnings correspond to anomalies that directly affect grid connection stability (such as severe voltage / frequency deviations or excessive generator vibration), and are alerted through audible and visual alarms and by pushing emergency information to the maintenance terminal; Level 2 warnings correspond to anomalies that affect the unit's auxiliary functions (such as low cooling water pressure or insufficient oil tank level), and are alerted through system pop-ups and SMS reminders.

[0107] By combining sub-region division information (to determine the level of the region to which the anomaly belongs) and sensor deployment location (to locate the specific data collection point), the faulty component can be accurately located (e.g., if a sensor collects an abnormal stator temperature, the location is traced to the stator winding), and a location report can be generated. The report includes the real-time trend of abnormal parameters (e.g., the temperature rises from 80℃ to 130℃ within 10 minutes) and the operating status of related components (e.g., the current speed and current of the corresponding cooling fan), providing maintenance personnel with a basis for troubleshooting.

[0108] Corresponding to the aforementioned embodiments of the intelligent multi-point monitoring method for generator sets, this application also provides embodiments of an intelligent multi-point monitoring system for generator sets.

[0109] Figure 5 This is a block diagram illustrating an intelligent multi-point monitoring system for a generator set according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a multi-point area division module 401, a multi-dimensional data monitoring module 402, and a power generation and grid connection anomaly warning module 403; wherein:

[0110] The multi-point area division module 401 is used to acquire generator set data and divide the generator set into primary and secondary monitoring sub-areas.

[0111] The multi-dimensional data monitoring module 402 is used to deploy multiple types of sensors to collect multi-dimensional parameters of the sub-area in real time, according to the monitoring requirements of key components in each monitoring sub-area.

[0112] The power generation and grid connection anomaly warning module 403 is used to analyze multi-dimensional parameters of sub-regions in real time based on multi-dimensional parameters, identify abnormal power generation and grid connection situations, and perform multi-level warnings and anomaly location.

[0113] In this embodiment, the multi-point area division module 401 acquires generator set data and divides the generator set into primary and secondary monitoring sub-areas; the multi-dimensional data monitoring module 402 deploys multiple types of sensors according to the monitoring requirements of key components in each monitoring sub-area, and collects multi-dimensional parameters of the sub-area in real time; the power generation and grid connection anomaly warning module 403 analyzes the multi-dimensional parameters of the sub-area in real time based on the multi-dimensional parameters, identifies abnormal power generation and grid connection situations, and performs multi-level warnings and anomaly location; through the above methods, the efficiency and adaptability of anomaly identification are improved, thereby enhancing the safety of generator set operation and grid connection reliability.

[0114] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0115] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0116] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the intelligent multi-point monitoring method for generator sets as described above. Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities within a generator set intelligent multi-point monitoring system provided in an embodiment of the present invention, except... Figure 6 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0117] Accordingly, this application also provides a computer-readable storage medium storing computer instructions thereon, which, when executed by a processor, implement the intelligent multi-point monitoring method for generator sets as described above. The computer-readable storage medium can be an internal storage unit of any data processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing device, and can also be used to temporarily store data that has been output or will be output.

[0118] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0119] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for intelligent multi-point monitoring of generator sets, characterized in that, Includes the following steps: Acquire generator set data and divide the generator set into primary and secondary monitoring sub-areas; Based on the monitoring requirements of key components in each monitoring sub-area, multiple types of sensors are deployed to collect multi-dimensional parameters of the sub-area in real time; the specific process is as follows: Analyze the operating characteristics of key components in the first-level sub-region and determine the types of parameters to be monitored, including temperature, vibration, voltage, current, and rotational speed. For key components in the secondary sub-region, determine the types of parameters to be monitored, including pressure, flow rate, liquid level, and operating status signals; Based on the parameter monitoring accuracy requirements and the environmental characteristics of the sub-area, select the sensor type and deploy the sensor points. Configure the sensor acquisition frequency, acquire multi-dimensional parameters, and perform preliminary preprocessing on the multi-dimensional parameters; Based on real-time analysis of multi-dimensional parameters in sub-regions, abnormal power generation and grid connection situations are identified, and multi-level warnings and anomaly location are provided. In the steps of acquiring generator set data and dividing the generator set into primary and secondary monitoring sub-regions: Collect the overall structural parameters, operating characteristic data and historical monitoring records of the generator set, and delineate the distribution range of the core area and auxiliary area of ​​the generator set; The core area is designated as a first-level monitoring sub-area, and the auxiliary area is designated as a second-level monitoring sub-area; Establish a sub-region boundary identifier and association table to determine the spatial connection and data interaction interface between the first-level and second-level sub-regions; the sub-region association table includes the following fields: sub-region ID, boundary coordinates, associated sub-region ID, data interaction interface type, and interaction frequency; In the process of designating the core area as a primary monitoring sub-area and the auxiliary area as a secondary monitoring sub-area: Based on real-time monitoring of unit operation, key component upgrades, and historical fault statistics, the first-level and second-level sub-regions are dynamically adjusted; based on the recalculated functional weights, the boundaries and levels of the sub-regions are adjusted; the sub-region association table is updated, and the interface rules between the first-level and second-level sub-regions are adjusted. If a secondary sub-region is upgraded to a core functional support point, its functional weight will be increased; if some devices in a primary sub-region are converted to backup devices, their functional weight will be reduced.

2. The intelligent multi-point monitoring method for generator sets as described in claim 1, characterized in that, In the steps of real-time analysis of multi-dimensional parameters in sub-regions, identification of abnormal power generation and grid connection situations, and multi-level warning and anomaly location: Construct a normal operation threshold model for core parameters in the first-level sub-region and a correlation model for auxiliary parameters in the second-level sub-region; The multi-dimensional parameters collected in real time are compared and analyzed with the corresponding model, and anomaly identification requests are triggered based on the analysis results. Warning levels are classified according to the importance and scope of impact of abnormal parameters, and multiple levels of warnings are issued. Based on the sub-region division information and sensor deployment locations, the faulty component is located, and a location report containing the trend of abnormal parameter changes and the status of related components is generated.

3. The intelligent multi-point monitoring method for generator sets as described in claim 2, characterized in that, In the step of comparing and analyzing the multi-dimensional parameters collected in real time with the corresponding model, and triggering anomaly identification requests based on the analysis results: An anomaly detection request is triggered when the analysis results show that either the parameters of the first-level sub-region exceed the threshold or the correlation between the parameters of the second-level sub-region is abnormal.

4. A generator set intelligent multi-point monitoring system, employing the generator set intelligent multi-point monitoring method as described in claim 1, characterized in that, This includes a multi-point area division module, a multi-dimensional data monitoring module, and a power generation grid connection anomaly warning module; among which: The multi-point area division module is used to acquire generator set data and divide the generator set into primary and secondary monitoring sub-areas. The multi-dimensional data monitoring module is used to deploy multiple types of sensors to collect multi-dimensional parameters of the sub-area in real time, based on the monitoring needs of key components in each monitoring sub-area. The power generation and grid connection anomaly warning module is used to analyze multi-dimensional parameters of sub-regions in real time based on multi-dimensional parameters, identify abnormal power generation and grid connection situations, and perform multi-level warnings and anomaly location.

Images