Digital and big data thermal power safety production management method and system

Abstract

The invention belongs to the field of thermal power safety production management, and particularly relates to a digital and big data thermal power safety production management method and system. Obtaining first data; inputting the first data into the operation model, and judging the type of the first data; and performing fault alarm classification on the operation model, and establishing a fault alarm rule. While the operation efficiency of the equipment is improved, the life cycle management of the equipment is enhanced, the service life of the equipment is prolonged, and the maintenance cost is reduced. The whole method improves the intelligent level of thermal power plant management, provides accurate support for decision making, and reduces the risk of production interruption.

Description

Technical Field

[0001] The present invention belongs to the field of thermal power production safety management, and specifically relates to a digital and big data thermal power production safety management method and system. Background Art

[0002] As an important part of global power production, thermal power generation has gradually become a key link in the modern power industry as energy demand continues to grow. With the rapid development of digital technology and big data analysis technology in recent years, the production management of traditional thermal power plants has gradually shifted from empirical management to data-driven management. The widespread application of digital and big data technologies has significantly improved the capabilities of thermal power plants in equipment monitoring, operation optimization, fault warning, etc., laying a technical foundation for improving the safety, economy and reliability of unit operation.

[0003] In the operation and management of thermal power plants, the unit operating parameters are an important basis for judging the operating status and safety performance of equipment. Traditional monitoring methods mainly rely on fixed threshold alarms and manual experience judgment. Although this method has certain practical effects, it has obvious limitations: on the one hand, a single threshold cannot fully reflect the dynamic characteristics of equipment operation under complex working conditions, which can easily lead to false alarms and missed alarms; on the other hand, relying on manual analysis has problems such as low data processing efficiency and delayed troubleshooting. In addition, most existing monitoring systems are single-parameter monitoring, lack multi-parameter correlation analysis and comprehensive evaluation capabilities, and cannot effectively extract potential risk characteristics of equipment operation from massive real-time data.

[0004] The present invention introduces big data technology, intelligent model training and optimization into the field of thermal power safety management, which can not only realize the accurate analysis and optimization of the unit operating parameters, but also significantly improve the system's fault warning capability and operational reliability, thereby effectively solving the deficiencies in the existing technology and meeting the actual needs of modern thermal power plants in safe production management. Summary of the invention

[0005] In view of the above problems existing in the prior art, the present invention is proposed.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a digital and big data thermal power safety production management method, comprising: obtaining first data;

[0007] inputting the first data into the running model;

[0008] Classify the fault alarms of the running model and establish fault alarm rules.

[0009] As a preferred solution of the digital and big data thermal power safety production management method described in the present invention, wherein: the first data is obtained by calculation, and the first data is calculated, and the first data is judged according to the calculation result.

[0010] As a preferred solution of the digital and big data thermal power safety production management method described in the present invention, wherein: the determination of the first data type includes:

[0011] If the first data is less than or equal to the first-level threshold, the data is judged to be green data;

[0012] If the first data is greater than the first threshold and less than the second threshold, it is judged as yellow data;

[0013] If the first data is greater than or equal to the secondary threshold, it is judged as red data;

[0014] The first-level threshold and the second-level threshold are dynamically adjusted through a multi-level collaborative dynamic adjustment mechanism.

[0015] As a preferred solution of a digital and big data thermal power safety production management method described in the present invention, the multi-level collaborative dynamic adjustment mechanism includes:

[0016] Real-time monitoring data and historical data through the basic data layer;

[0017] Based on the data transmitted by the basic data layer, a calculation model is established to predict the operating status of the equipment;

[0018] When an abnormality occurs in the operating status, the first and second level thresholds are adjusted dynamically through feedback from the prediction results of the calculation model and the historical data collected by the basic data layer.

[0019] As an optimal solution of the digital and big data thermal power safety production management method described in the present invention, the fault alarm rule includes: when the first input data is green data, the model diagnosis equipment is run to determine whether it continues to operate healthily; if the detection result is that it continues to operate healthily, the data change trend is monitored; if the detection result is that it cannot maintain healthy operation, the host computer prompts manual verification; if the data change trend deviates from the green data interval, a first-level data judgment is performed again; if the judgment result is that the data detection is correct, a response data detection is performed according to the data color interval; if the judgment result is that there is no trend change, the equipment is judged to be fault-free.

[0020] As an optimal solution of the digital and big data thermal power safety production management method described in the present invention, the fault alarm rule includes: when the first input data is yellow data, the equipment enters an alert state and performs data trend judgment. If the trend is judged to be the yellow data turning into the green data interval, it is checked according to the green data standard. If the trend is judged to be stable as the yellow data trend, the equipment enters an alert state and increases the data detection frequency. If the trend of the yellow data shows entering the red data interval, the data is fed back to the first data to judge whether there is a false alarm. If there is a false alarm, the rule judgment is performed based on the re-checked data. If there is no false alarm, the red data rule judgment is performed.

[0021] As a preferred solution of the digital and big data thermal power safety production management method described in the present invention, the model is trained to learn the model, including a training method using a supervised learning method, and the fault alarm rule includes that when the first input data is red data, a red data rule judgment is performed, the real-time data is re-collected and a first data judgment is performed on the real-time data. If the judgment result is red data, it is judged as a serious fault, and emergency processing is automatically performed to stop the faulty equipment, start the backup equipment, and automatically adjust the parameters. If the model automation fails to solve the problem, the host computer will urgently remind the on-site operating personnel to intervene manually, and prompt the inspection of equipment components.

[0022] As a preferred solution of a digital and big data thermal power production safety management system described in the present invention, it includes: a collection module, a calculation module, and a judgment and alarm module;

[0023] The acquisition module obtains first data;

[0024] The calculation module inputs the first data into the operation model;

[0025] The pre-judgment alarm module classifies the operating model into fault alarms and establishes fault alarm rules.

[0026] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of any one of the methods of digital and big data thermal power safety production management are implemented.

[0027] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method described in any one of a digital and big data thermal power safety production management method are implemented.

[0028] Beneficial effects of the present invention: The digital and big data thermal power production safety management method of the present invention dynamically adjusts the primary and secondary thresholds by real-time monitoring of equipment data and adopting a multi-level collaborative dynamic adjustment mechanism, thereby solving the problem that fixed thresholds are difficult to adapt to changes in equipment operating conditions and improving the safety of equipment operation. Through intelligent classification of equipment data (green, yellow, and red), accurate fault alarms are achieved, and corresponding treatment measures can be taken at different risk levels to reduce false alarms and missed alarms. The operating model analyzes the trend changes of the equipment, identifies potential faults in a timely manner, automatically takes warnings, increases the detection frequency, or feedbacks data, reduces manual intervention, and improves the accuracy of fault diagnosis. Emergency processing can be automatically performed, and standby equipment can be switched to ensure production safety. Combining big data with artificial intelligence technology, the present invention enhances equipment life cycle management, extends equipment service life, and reduces maintenance costs while improving equipment operating efficiency. The overall method improves the level of intelligence in thermal power plant management, provides accurate support for decision-making, and reduces the risk of production interruption. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0030] Figure 1 A flowchart of a digital and big data thermal power safety production management method provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0032] Example 1

[0033] Reference Figure 1 , which is the first embodiment of the present invention, and provides a digital and big data thermal power safety production management method, including:

[0034] S1: Obtain first data.

[0035] It should be noted that the first data is obtained by calculation, and the first data is calculated, and the first data is judged according to the calculation result.

[0036] Furthermore, the raw sensor data is preprocessed. Preprocessing includes data denoising, data cleaning, missing value filling, etc. to ensure the integrity and accuracy of the data. Common processing methods include moving average method, smoothing filter, Kalman filter, etc.

[0037] It should be noted that in the embodiments of the present application, the first data is an aggregate value of multiple sensor data as required. For example, the readings of multiple temperature sensors can be obtained by weighted average, arithmetic average, etc. to obtain an overall device temperature data, or a weighted average of multiple device operating parameters. These aggregate values ​​are the first data.

[0038] It should be noted that after the first data is obtained, it is judged by a preset threshold and calculation model, and then classified into green, yellow or red data. The specific calculation steps are as follows:

[0039] It is necessary to set a primary threshold (the boundary between green and yellow) and a secondary threshold (the boundary between yellow and red). These thresholds can be set based on historical data, equipment operating standards or empirical rules, or dynamically adjusted through data analysis and modeling processes.

[0040] It should be noted that if the first data is less than or equal to the first-level threshold, the data is judged to be green data;

[0041] If the first data is greater than the first threshold and less than the second threshold, it is judged as yellow data;

[0042] If the first data is greater than or equal to the secondary threshold, it is judged as red data;

[0043] Since the operating status of the equipment may be affected by many factors (such as equipment aging, changes in the external environment, etc.), the primary and secondary thresholds need to be continuously optimized and adjusted through a multi-level collaborative dynamic adjustment mechanism to ensure that these thresholds can adapt to changes in the equipment under different conditions. This adjustment mechanism dynamically adjusts the thresholds by learning the historical data of the equipment and feedback of real-time data to achieve the purpose of accurate monitoring.

[0044] It should be noted that in the embodiment of the present application, the multi-level collaborative dynamic adjustment mechanism is a complex and intelligent control mechanism that aims to dynamically adjust the key parameters of the system, especially the primary and secondary thresholds, according to the equipment operating conditions, historical data, and real-time feedback. This mechanism ensures that the equipment can respond in real time and maintain safe operation under different working conditions, loads, and other changing conditions. The following is a detailed adjustment process of the mechanism.

[0045] Data acquisition layer (basic data layer): The data acquisition layer is the foundation of the entire mechanism and is responsible for collecting raw data from various sensors and devices in real time. The data includes but is not limited to temperature, pressure, vibration, current, voltage, etc. These data will be used for subsequent analysis and judgment. Various operating indicators of the equipment are collected by sensors and transmitted to the data processing system. The data collection frequency is usually high (for example, once every second or every minute) to ensure that the system has a real-time understanding of the equipment status. In addition to real-time data, it is also necessary to accumulate historical operating data of the equipment in order to analyze the long-term trends, periodic changes and potential failure modes of the equipment. Historical data will serve as a reference for dynamically adjusting thresholds.

[0046] The data processing layer receives data from the data acquisition layer and performs preliminary processing and analysis. The main task of this layer is to calculate the data through the algorithm model, analyze the current operating status of the equipment, and predict future trends. The raw data usually contains noise or outliers. The data processing layer will first clean the data and remove invalid or erroneous values. The data is standardized to meet the unified metric standards. The current status of the equipment is evaluated through a variety of algorithms (such as regression analysis, time series analysis, machine learning, etc.). For example, historical data and real-time data are used to evaluate the health status of the equipment to determine whether the equipment is in a healthy range and whether there are signs of failure.

[0047] The prediction model layer is the core part of the multi-level collaborative dynamic adjustment mechanism. It is responsible for predicting the future state based on the data analysis results, and then dynamically adjusting the threshold. Use the neural network model algorithm based on historical data to predict the future operating state of the equipment. For example, based on the current load, operating time, temperature changes, etc., predict the operating status of the equipment in the next few hours or days. Predict whether the equipment is likely to fail, or how likely the failure is. For different equipment failure modes (such as mechanical failure, electrical failure, etc.), the model will make corresponding predictions based on historical data and equipment type. The prediction model not only outputs future operating trends, but also adjusts the system thresholds based on the prediction results. For example, if the system predicts that the equipment load will increase significantly, the model can adjust the threshold in advance to ensure that the equipment is always in a safe operating range.

[0048] In the embodiments of the present application, it should be noted that the abnormal operating state includes: the difference between real-time monitoring data and historical data reaches a set threshold, the equipment predicts that the equipment state is close to failure, and the equipment load or environmental conditions change significantly.

[0049] It should be noted that when the difference between real-time monitoring data and historical data reaches the set threshold, various real-time data of the equipment, such as temperature, pressure, current, load, etc., are monitored in real time through sensors or data acquisition systems and transmitted to the data processing system. The historical data of normal operation of the equipment includes long-term records of equipment operating status (such as temperature, pressure, etc.). These data serve as the standard operating range of the equipment. The system will set a data deviation threshold, that is, when the deviation between real-time data and historical data exceeds this threshold, the dynamic adjustment mechanism is triggered. By comparing real-time data with historical data, the system detects the difference. If the current operating data of the equipment deviates greatly from the historical data (exceeding the set threshold), it means that the operating status of the equipment has changed, and the threshold of the equipment may need to be dynamically adjusted. Based on the detected difference, the system adjusts the threshold in the following ways:

[0050] If a key parameter of the device (such as temperature or pressure) exceeds the normal range of historical data, the system will increase the threshold range. For example, if the temperature of the device should be within 80°C under normal load, but the current temperature has reached 85°C, the first-level threshold can be increased to 85°C. When the device load or environment changes greatly, the threshold adjustment can be more substantial. Assuming that the external temperature change causes the cooling efficiency to decrease, the system can appropriately increase the temperature threshold of the device to ensure that the device can adapt to the new operating environment. After the threshold is adjusted, the system continues to monitor the real-time data of the device. If the device returns to the normal range, the threshold will be further adjusted to ensure that the device always operates within an appropriate safety range.

[0051] Furthermore, when the equipment prediction model determines that the equipment state is close to failure, the equipment prediction model is constructed based on historical data, real-time monitoring data of the equipment, and machine learning or regression analysis algorithms to predict the operating state of the equipment in the future. The system obtains the working parameters of the equipment in real time, and determines through prediction that these parameters may enter a faulty or abnormal state in the future (such as a continuous increase in temperature and pressure). The equipment's fault warning mechanism sets multi-level thresholds (such as green, yellow, and red warning values) based on the normal working range of the equipment. By analyzing real-time and historical data, it is determined that the equipment may enter a faulty state. For example, the model calculates that parameters such as temperature and pressure will exceed the safe range in the next period of time, thereby causing a fault. When the prediction model determines in advance that the equipment enters a red alert state, the system will start the threshold dynamic adjustment mechanism:

[0052] If certain key indicators of the equipment (such as temperature and pressure) will approach or exceed the currently set secondary threshold within a certain period of time in the future, the system will adjust the threshold in advance to expand the safe operating range. For example, if the prediction model shows that the temperature will reach 90°C in 2 hours, and the current secondary threshold is 85°C, the secondary threshold can be raised to 95°C in advance to reduce the risk of false alarms and missed alarms. After the threshold is adjusted, the system immediately issues a fault warning to the monitoring personnel, or initiates automated protection measures (such as starting backup equipment, automatically adjusting parameters, etc.). After the threshold is adjusted, the system will continue to provide dynamic feedback based on the actual operation of the equipment. If the operating status of the equipment is consistent with the prediction results, the new threshold is maintained; if the prediction deviates, the threshold will be further adjusted according to the actual situation.

[0053] Furthermore, when the equipment load or environmental conditions change significantly, the change in equipment load directly affects its working state, and the system will monitor the load fluctuations of the equipment in real time. Changes in the external environment (such as temperature, humidity, etc.) will also affect the operating state of the equipment. The system collects this data through environmental sensors. Based on the design parameters and operating conditions of the equipment, the system sets the normal operating range of each key parameter, as well as the safe operating range of the equipment under different loads and environments. The system monitors changes in equipment load or fluctuations in the external environment in real time. If the load increases significantly or the ambient temperature, humidity and other conditions change significantly (for example, the outside temperature rises sharply), the system will immediately detect these changes and evaluate whether the equipment needs to adjust the threshold. Based on load changes or environmental changes, the system will adjust the threshold:

[0054] If the load on the device increases significantly, it may cause temperature rise, pressure increase, etc. The system will increase the thresholds of parameters such as temperature and pressure. For example, when the load on the device increases, the temperature threshold can be adjusted upward to ensure that the device can still operate safely under a higher load. When the ambient temperature, humidity and other conditions change significantly, the system may adjust the parameter thresholds related to these environmental factors. For example, if the external temperature increases, resulting in a decrease in cooling efficiency, the system will adjust the temperature threshold to ensure that the device can maintain normal operation under the new environmental conditions. After the threshold is adjusted, the system will continue to monitor the operating status of the device to ensure that the device can operate stably under the new load or environmental conditions. If the load or environmental conditions return to normal levels, the threshold will be automatically adjusted back to the original level.

[0055] It should be noted that the first-level threshold (i.e., the upper limit of the green data interval) will be automatically adjusted dynamically according to the real-time operating status of the equipment. For example, when the equipment is under high-load operation, the system may appropriately increase the first-level threshold to allow data fluctuations within a certain range to avoid frequent alarms. During the long-term operation of the equipment, the system will automatically adjust the setting of the first-level threshold by learning the fluctuation patterns in historical data. For example, if the equipment exhibits large temperature fluctuations in a specific season or load range, the first-level threshold will be appropriately adjusted to adapt to such fluctuations. When the operating status of the equipment tends to be normal or gradually recovers, the first-level threshold will automatically be called back to the default value or optimized according to the new operating data.

[0056] The secondary threshold (i.e., the lower limit of the red data interval) is usually used to determine whether the equipment has entered an emergency fault state. The system will dynamically adjust the sensitivity of the secondary threshold based on factors such as the equipment load and operating environment. For example, under certain extreme conditions, the system may lower the secondary threshold in advance to capture potential equipment failures earlier. For equipment with large load changes, the secondary threshold will be adjusted according to the load changes. For example, when the equipment load increases, the secondary threshold will be appropriately lowered to reduce the system's "safety threshold" area and ensure that equipment problems are discovered in a timely manner. When the prediction model determines that the equipment may enter a high-risk area, the secondary threshold will automatically tighten, increase the frequency of monitoring abnormal equipment conditions, and prevent potential failures.

[0057] S2: Input the first data into the running model.

[0058] It should be noted that in the embodiment of the present application, the operation model uses the support vector machine (SVM) algorithm to classify the operation status of the device. SVM is selected as the core classification algorithm because it can effectively process data in high-dimensional space and map low-dimensional data to high-dimensional space through kernel functions, thereby being able to handle complex nonlinear relationships. The following is a detailed description of how to construct and use the SVM algorithm in this patent:

[0059] The operation data of the equipment will be collected in real time, including but not limited to temperature, pressure, current, voltage, vibration and other multi-dimensional data. These data come from the sensors of the equipment and are usually collected at high frequency. These data may contain certain noise, so the data needs to be preprocessed, including data cleaning, denoising, standardization and other steps.

[0060] Generate a training data set from the historical data of the equipment and known failure cases. This data set contains the characteristic data and corresponding labels (such as healthy, warning, and fault) of the equipment in different operating states. Since the relationship between the equipment operating state and multiple factors (such as temperature, pressure, current, etc.) is nonlinear, SVM uses the radial basis function (RBF) kernel to handle this nonlinear relationship. The RBF kernel function can map low-dimensional inputs to high-dimensional space, and then find a hyperplane that can distinguish different states. SVM finds the optimal hyperplane by solving an optimization problem. The goal of this optimization problem is to maximize the classification interval and ensure that the sample points of different categories are as far away from the decision boundary as possible. After the model training is completed, the obtained SVM model can judge the operating state of the equipment based on the input equipment characteristic data.

[0061] The real-time monitoring data of the equipment (such as temperature, pressure, current, etc.) is input into the SVM model as a feature. The SVM uses a trained hyperplane to map the input data to a high-dimensional space and judges the current state of the equipment based on the closest hyperplane. Each input data will be divided into different categories, indicating whether the equipment is healthy, in an alert state, or in a fault state.

[0062] Since the operating status of the device may be affected by factors such as environmental changes and device aging, the relationship between the device status and characteristics is dynamically changing in actual applications. Therefore, the SVM model needs to be continuously optimized and updated during the actual operation process.

[0063] When new equipment operation data (including fault data) is obtained through real-time monitoring, the system will compare this data with the prediction results to determine whether a fault or other abnormal state has occurred. If the system finds that the original model prediction is wrong or the performance is poor, the model can be updated through online learning. The SVM algorithm can use the incremental learning method to optimize the model. Each time new data is introduced, SVM can adjust the classification hyperplane and optimize the decision boundary through incremental updates, so that the model is more adaptable to the new equipment operation status.

[0064] S3: Classify the fault alarm of the running model and establish fault alarm rules.

[0065] It should be noted that when the first data is judged as green data, it means that the equipment is operating normally and all parameters are within a safe range. At this time, the running model will perform the following operations: The running model will monitor the health status of the equipment and ensure that it continues to operate within a safe range. If the status of the equipment changes, the model will determine whether it can still maintain the range of healthy operation. If the equipment is still in a green state, the system will monitor the change trend of its data. If the change trend deviates from the green data interval (that is, there is a slight fluctuation in the operating status of the equipment), the model will re-judge the data and determine whether the change is within the error range. If there is no false alarm, continue to monitor the equipment; if the fluctuation trend cannot maintain the green data interval, a manual verification warning will be triggered to prompt the on-site personnel to pay attention. If there is no trend change and the first data is judged correctly, the equipment is considered to have no faults and the system continues to operate normally.

[0066] Furthermore, the fault alarm rule includes that when the first data is judged as yellow data, it indicates that the equipment enters an alert state and there is a risk of potential failure. At this time, the model will perform the following operations: the system will determine whether the trend of the yellow data is stable. If the yellow data tends to the green interval (that is, the equipment status returns to normal), it will be checked according to the green data standard, and the equipment operating parameters will be readjusted to return to normal status. If the trend judgment shows that the equipment status is stable in the yellow interval, the system will keep the equipment in an alert state and increase the frequency of data detection to ensure that potential faults are discovered in time. If the yellow data trend shows that it enters the red data interval (that is, a precursor to a serious fault in the equipment), the system will feed the data back to the first data judgment module to determine whether there is a false alarm. If it is confirmed to be a false alarm, the system will re-judge the rules based on the new data; if it is confirmed that the trend is a real fault, it will enter the red data processing rules.

[0067] The fault alarm rules include that when the first data is judged to be red data, it indicates that a serious fault has occurred in the equipment. At this time, the system will execute the following rules: the system will re-collect real-time data and make the first data judgment again. If the data is confirmed to be red, it is judged to be a serious fault, and the system will immediately start the emergency processing mechanism: the system will immediately stop the operation of the faulty equipment to avoid further expansion of the fault. If there is a spare device, the system will automatically enable the spare device to take over the work of the faulty equipment to ensure the normal operation of the thermal power plant. The system will automatically adjust the parameters of the equipment according to the real-time data, try to repair the fault and restore the normal operation of the equipment. If the automation model cannot solve the problem (such as the fault is too complex or urgent), an emergency reminder will be sent to the on-site operator through the host computer, prompting the equipment components to be checked, and recommending manual intervention measures for fault diagnosis and repair.

[0068] Fault alarm rules can achieve accurate and timely fault warnings in the operation of thermal power plant equipment by combining data monitoring, trend judgment, dynamic feedback, and automatic and manual intervention. This rule effectively improves the speed of equipment fault detection and response, avoids the huge impact of equipment failure on production, and ensures the safe and stable operation of thermal power plants.

[0069] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0070] Example 2

[0071] The second embodiment of the present invention is different from the previous embodiment in that:

[0072] The digital and big data thermal power production safety management method of the present invention can be implemented in the form of a software functional unit and sold or used as an independent product. The software product can be stored in a computer-readable storage medium and executed by different devices (such as a personal computer, a server or a network device, etc.). Computer-readable storage media include various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), disks, and optical disks. In this way, users can easily install and execute the software to realize functions such as equipment monitoring, data analysis, and fault warning in thermal power plants.

[0073] In the present invention, the logic and steps of the functional modules are composed of instructions executed by a computer and stored in a computer-readable medium. The software is implemented by an instruction execution system, device or equipment (such as a computer system, a system including a processor, etc.), including the collection, calculation, judgment, fault diagnosis and alarm, dynamic adjustment and other processes of real-time data. Specifically, the operation model determines whether the collected data is in the preset green, yellow or red interval, and triggers different alarm rules according to the change trend of the data to ensure the safe operation of the thermal power equipment.

[0074] In addition, the technical solution of the present invention can also be implemented through hardware, software, firmware or a combination thereof. For example, in terms of hardware, electronic devices, magnetic devices, memory, etc. can be used to process digital signals through programming; in terms of software, the program stored in the memory will perform data collection and judgment according to the set steps, and trigger corresponding alarms and processing measures; if it is implemented in the form of firmware, the instructions will be embedded in the device to directly control the hardware work. This combination of software and hardware can efficiently complete various tasks of thermal power production safety management and improve the safety and intelligence level of equipment operation.

[0075] Through the integration of software products and hardware devices, the invented functional modules can be executed on different computer or device platforms, flexibly adapting to the different needs of thermal power plants and realizing comprehensive safety production monitoring and management. This implementation method can not only improve the efficiency of the system, but also continuously improve the intelligent level of safety management through software updates and function expansion.

[0076] Example 3

[0077] The third embodiment of the present invention provides a digital and big data thermal power production safety management system, which is characterized by: a collection module, a calculation module, and a judgment and alarm module;

[0078] The acquisition module is responsible for acquiring first data related to the operating status of the device in real time. These data include but are not limited to key operating parameters such as temperature, pressure, current, voltage, load, etc. of the device. The acquisition module uses a variety of data acquisition technologies, such as sensors, data interfaces, etc., to ensure the accuracy and real-time nature of the data.

[0079] The acquisition module is the foundation of the entire system, which provides data support for subsequent calculations and judgments. Through high-precision acquisition equipment and perfect network interfaces, the system can obtain detailed information on the device status in real time and provide a reliable data basis for subsequent judgments and alarms.

[0080] The calculation module, the main task of the calculation module is to input the collected first data into the operation model for processing. The operation model predicts, calculates and analyzes the operation status of the equipment through a preset mathematical model (such as a regression model, a neural network model, a fuzzy control model, etc.). These calculation results include whether the parameters such as the load and temperature of the equipment are within the normal range, whether there is a risk of failure or equipment damage.

[0081] The calculation module is not only responsible for data processing, but also for real-time evaluation of equipment status through dynamic algorithms and prediction models. By integrating historical data and real-time data of equipment, the calculation module can predict the future operation trend of equipment and discover potential problems in time, thereby reducing the risk of false alarms and missed alarms. The close cooperation between the calculation module and the acquisition module ensures the consistency and efficiency of data during acquisition, transmission and processing.

[0082] The pre-judgment alarm module and the judgment alarm module compare the result output by the calculation module with the fault alarm rule, and classify the device status according to the predetermined rule. According to the different device status, the judgment module will classify the device into three different states: green, yellow and red.

[0083] Sensors and data acquisition devices are used to obtain real-time data from the equipment and transmit the data to the computer system through communication protocols. The calculation module and judgment alarm module rely on powerful computing power and intelligent algorithms to monitor and alarm the equipment status through real-time calculation and logical judgment. The acquisition module, calculation module and judgment alarm module work together in the background system to ensure the efficiency and accuracy of data transmission, calculation analysis and alarm response.

[0084] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A digital and big data thermal power production safety management method, characterized by: include: obtaining first data; Inputting the first data into the running model to determine the first data type; Classify the fault alarms of the running model and establish fault alarm rules.

2. The digital and big data thermal power production safety management method according to claim 1 is characterized by: The first data is obtained by calculation, and the first data is compared to determine the first data type.

3. The digital and big data thermal power production safety management method according to claims 1 and 2 is characterized by: The determining of the first data type includes: If the first data is less than or equal to the first-level threshold, the data is judged to be green data; If the first data is greater than the first threshold and less than the second threshold, it is judged as yellow data; If the first data is greater than or equal to the secondary threshold, it is judged as red data; The first-level threshold and the second-level threshold are dynamically adjusted through a multi-level collaborative dynamic adjustment mechanism.

4. The digital and big data thermal power production safety management method according to claim 3 is characterized by: The multi-level collaborative dynamic adjustment mechanism includes: Real-time monitoring data and historical data through the basic data layer; Based on the data transmitted by the basic data layer, a calculation model is established to predict the operating status of the equipment; When an abnormal operating state occurs, the first and second level thresholds are dynamically adjusted through feedback from the calculation model prediction results and historical data collected by the basic data layer.

5. The digital and big data thermal power production safety management method according to claim 1, 2 or 4, characterized in that: The fault alarm rule includes, when the first data input is green data, running the model to diagnose whether the equipment continues to operate healthily, if the detection result is that the equipment continues to operate healthily, monitoring the data change trend, if the detection result is that the equipment cannot maintain healthy operation, prompting the host computer to conduct manual verification; If the data change trend deviates from the green data interval, the first-level data judgment is performed again. If the judgment result is that the data detection is correct, the corresponding data detection is performed according to the data color interval. If the judgment result is that there is no trend change, it is judged that the equipment is not faulty.

6. The digital and big data thermal power production safety management method according to claim 5, characterized in that: The fault alarm rules include: when the first input data is yellow data, the device enters an alert state and performs data trend judgment. If the trend is judged to be the yellow data turning into the green data interval, it is checked according to the green data standard. If the trend is judged to be stable as the yellow data trend, the device enters an alert state and increases the data detection frequency. If the trend of the yellow data shows entering the red data interval, the data is fed back to the first data to judge whether there is a false alarm. If there is a false alarm, the rule judgment is performed based on the re-checked data. If there is no false alarm, the red data rule judgment is performed.

7. The digital and big data thermal power production safety management method according to claim 6, characterized in that: The fault alarm rules include: when the first input data is red data, a red data rule judgment is performed, real-time data is re-collected and a first data judgment is performed on the real-time data. If the judgment result is red data, it is judged as a serious fault, and emergency processing is automatically performed to stop the faulty equipment, start the backup equipment, and automatically adjust the parameters. If the model automation does not solve the problem, the host computer will urgently remind the on-site operators to intervene manually and prompt the equipment components to be checked.

8. A digital and big data thermal power production safety management system, characterized by: It includes collection module, calculation module and judgment and alarm module.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of a digital and big data thermal power safety production management method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions. When the execution instruction is executed by the processor, the steps of a digital and big data thermal power safety production management method as described in any one of claims 1 to 7 are implemented.

Images