An intelligent monitoring and station operation and maintenance method, system, product and medium

Abstract

An intelligent monitoring and station operation and maintenance method, system, product, and medium. The method includes: combining the real-time operation data and operation time of the device, obtaining an anomaly score according to the anomaly model, and classifying the anomaly level; in the case where the anomaly level is a warning anomaly, using the fault type map, calculating the correlation degree of the historical operation data corresponding to each fault type in the fault type map, and obtaining a fault type data group; sorting the fault types in the fault type data group from high to low according to the correlation degree, and the fault type with the highest correlation degree is the high-correlation fault type; retrieving the operation parameters and layout information of the device, simulating the high-correlation fault type, and obtaining real-time simulated operation data; in the case where the difference between the real-time simulated operation data and the real-time operation data is within the preset type judgment threshold range, determining that the real-time fault type is the high-correlation fault type. Implementing the technical solution provided by this application improves the accuracy of fault judgment in intelligent water monitoring.

Description

Technical Field

[0001] The present application relates to the field of monitoring or testing devices for such systems or units, and in particular to an intelligent monitoring and station operation and maintenance method, system, product and medium. Background Art

[0002] With the rapid development of Internet of Things technology, smart water management has become an indispensable part of modern urban management. It improves water resource utilization efficiency and reduces operating costs by collecting large amounts of data in real time.

[0003] At present, the operation and maintenance of monitoring stations still faces challenges, especially how to effectively predict and prevent equipment failures and ensure the stable operation of the system. The existing smart water management system uses a variety of advanced technologies to achieve effective monitoring and operation and maintenance of monitoring stations. Real-time data collection is carried out through sensors, with the help of integrated monitoring and the use of video monitoring as an aid. In terms of operation and maintenance, fault diagnosis is carried out through data analysis and machine learning, and remote control, operation and maintenance platforms and mobile terminal applications are used to improve operation and maintenance efficiency and flexibility.

[0004] However, although some monitoring stations can perform fault diagnosis after detecting abnormal data, they are prone to misjudgment or cannot accurately determine the type of fault. Summary of the invention

[0005] The present application provides an intelligent monitoring and station operation and maintenance method, system, product and medium for improving the accuracy of fault diagnosis in intelligent water monitoring.

[0006] In a first aspect of the present application, there is provided an intelligent monitoring and station operation and maintenance method, the method comprising:

[0007] Collect real-time operation data of the equipment; combine the real-time operation data and operation time data, obtain an anomaly score according to the anomaly model, and divide the anomaly level; when the anomaly level is a warning anomaly, combine the real-time operation data and equipment information, use the fault type map, calculate the correlation between the real-time operation data and the historical operation data corresponding to each fault type in the fault type map, and obtain a fault type data group; sort the fault types in the fault type data group from high to low according to the correlation, and the fault type with the highest correlation is a high-correlation fault type; retrieve the operation parameters and layout information of the equipment, simulate the high-correlation fault type, and obtain real-time simulated operation data; when the difference between the real-time simulated operation data and the real-time operation data is within a preset type judgment threshold range, judge the real-time fault type to be a high-correlation fault type.

[0008] In the above embodiment, by constructing an abnormal model, using a fault type map and simulating fault types, integrating various data, analyzing the equipment operating conditions, and accurately dividing the abnormal level, when the abnormal level is a warning abnormality, the fault type can be determined by calculating the correlation degree, and the accuracy of the fault type judgment can be further confirmed through simulation comparison, thereby improving the accuracy of fault judgment, effectively reducing misjudgment, and ensuring the stable operation of the intelligent water system.

[0009] In conjunction with some embodiments of the first aspect, in some embodiments, after combining the real-time operation data and the operation time data, obtaining an anomaly score according to an anomaly model, and dividing the anomaly levels, the method further includes:

[0010] When the abnormality level is a warning abnormality, a warning signal is issued.

[0011] In the above embodiment, by promptly issuing a warning signal when a warning anomaly is identified, relevant personnel can be informed of potential abnormal conditions of the equipment at the first time, effectively reducing the losses caused by equipment failure and ensuring the continuous and stable operation of the intelligent water system.

[0012] In combination with some embodiments of the first aspect, in some embodiments, when the abnormality level is a warning abnormality, issuing a warning signal specifically includes:

[0013] In the case where the abnormality level is a warning abnormality, a warning signal is issued, and after deleting the old abnormality score of the device in the abnormality score data group, the abnormality score is stored in the abnormality score data group; the data in the abnormality score data group is sorted from large to small, and the devices ranked within the top preset percentage threshold are marked as high-risk devices; a high-risk warning signal is sent; the high-risk warning signal is a signal that prompts that the high-risk device has a high-risk abnormality.

[0014] In the above embodiment, the score of the equipment with warning abnormalities in real time is stored in the abnormal score data group and the previously stored score is deleted. In the abnormal score data group, only the last abnormal score of each equipment with warning abnormalities is included. These abnormal scores are then sorted to screen high-risk equipment, which helps to arrange maintenance resources more efficiently, handle abnormal situations of high-risk equipment in a timely manner, reduce the probability of serious equipment failures, and ensure the stable operation of the entire system.

[0015] In conjunction with some embodiments of the first aspect, in some embodiments, after obtaining an abnormality score according to an abnormality model in combination with the real-time operation data and the operation time data, and dividing the abnormality level, the method further includes:

[0016] Collect the upstream and downstream water level difference data of the equipment and calculate the theoretical water flow data; when the difference between the theoretical water flow data and the real-time water flow data is greater than the preset water flow difference threshold, mark the real-time water flow data as suspicious data; when the abnormality level is no abnormality and the suspicious data exists, collect the real-time sound feature data at the water outlet pipe of the equipment; combine the real-time sound feature data and the pipe material and size data to calculate the sound water flow estimation value; when the difference between the sound water flow estimation value and the real-time water flow data is greater than the preset water flow difference threshold, mark the corresponding equipment as a high-risk equipment.

[0017] In the above embodiment, when the abnormality level is no abnormality, attention is still paid to the real-time water flow data that may have problems. The water flow is calculated by comparing the water level difference and sound characteristics, so that potential risks can be discovered in time, and equipment with potential hidden dangers can be marked as high risk, so that measures can be taken in advance to avoid equipment failure and ensure stable operation of the system.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, the sound water flow estimation value is calculated by combining the real-time sound feature data and the pipe material and size data, specifically including:

[0019] The sound water flow estimation value is calculated by combining the real-time sound feature data, the first formula, the pipe inner diameter data and the pipe material data in the pipe material and size data; wherein the first formula is: ; For the estimated value of the acoustic water flow, the pipe cross-sectional area , The comprehensive parameters related to the inner diameter of the pipe, pipe material and sound propagation characteristics , is the material data of the pipe. is a sound speed reference, is the standard deviation of the real-time sound frequency distribution in the real-time sound feature data, is the real-time sound intensity data in the real-time sound feature data, , To preset the coefficients related to sound intensity and water flow, is the correction coefficient function related to the frequency distribution.

[0020] In the above embodiment, the sound water flow estimation value is calculated based on the sound characteristics and pipeline parameters, and the correlation between the pipeline cross-sectional area, the sound intensity and the water flow, and the influence of the sound frequency distribution on the water flow state are comprehensively considered, thereby improving the accuracy and reliability of the water flow estimation.

[0021] In combination with some embodiments of the first aspect, in some embodiments, when the difference between the real-time simulation operation data and the real-time operation data is within a preset type judgment threshold range, after judging that the real-time fault type is a high-correlation fault type, the method further includes:

[0022] When the difference between the simulated operation data and the real-time operation data is not within the preset type judgment threshold range, all fault types in the fault type data group are simulated in sequence and the simulated operation data is calculated; when the difference between the first simulated operation data and the real-time operation data is within the preset type judgment threshold range, the real-time fault type is judged to be the first fault type corresponding to the first simulated operation data.

[0023] In the above embodiment, when the first simulated fault judgment fails, different fault types are simulated again to simulate and troubleshoot all possible fault types, thereby avoiding the situation where the fault cannot be accurately judged due to the failure of the initial simulation and improving the accuracy of fault judgment.

[0024] In conjunction with some embodiments of the first aspect, in some embodiments, after collecting the real-time operation data of the device, the method further includes:

[0025] When the real-time voltage data is greater than the preset voltage threshold, the real-time water flow data is less than the preset water flow threshold, and the real-time water flow outlet pressure data is less than the preset water flow outlet pressure data threshold, the device is turned off.

[0026] In the above embodiment, by monitoring key operating data in real time and comparing it with preset thresholds, the device is shut down in time when the data is abnormal, so that the device can avoid further damage when it may be facing danger or abnormal operating conditions.

[0027] In a second aspect, an embodiment of the present application provides an intelligent monitoring and station operation and maintenance system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent monitoring and station operation and maintenance system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0028] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the above-mentioned computer program product is run on an intelligent monitoring and station operation and maintenance system, the above-mentioned intelligent monitoring and station operation and maintenance system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0029] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on an intelligent monitoring and station operation and maintenance system, the intelligent monitoring and station operation and maintenance system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0030] It can be understood that the intelligent monitoring and station operation and maintenance system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the intelligent monitoring and station operation and maintenance method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, and will not be repeated here.

[0031] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0032] 1. This application constructs an abnormal model, uses fault type maps and simulates fault types, integrates various data, analyzes equipment operating conditions, and accurately divides abnormal levels. When the abnormal level is a warning abnormality, the fault type can be determined by calculating the correlation degree, and the fault type judgment can be further confirmed through simulation comparison. Whether it is accurate, it improves the accuracy of fault judgment, effectively reduces misjudgment, and ensures the stable operation of the intelligent water system.

[0033] 2. When the abnormality level is no abnormality, this application still pays attention to the real-time water flow data that may have problems. By calculating the water flow through the water level difference and sound characteristics for comparison, potential risks can be discovered in time, and equipment with potential hidden dangers can be marked as high-risk, so that measures can be taken in advance to avoid equipment failures and ensure stable operation of the system.

[0034] 3. When the first simulated fault judgment fails, the present application simulates different fault types again and performs simulation checks on all possible fault types, thereby avoiding the situation where the fault cannot be accurately judged due to the failure of the initial simulation and improving the accuracy of fault judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a structural diagram of an applicable system architecture of the intelligent monitoring and station operation and maintenance method in the embodiment of the present application;

[0036] Figure 2 It is a flow chart of the intelligent monitoring and station operation and maintenance method in the embodiment of the present application;

[0037] Figure 3 It is another flow chart of the intelligent monitoring and station operation and maintenance method in the embodiment of the present application;

[0038] Figure 4It is an exemplary hardware structure diagram of the intelligent monitoring and station operation and maintenance system in the embodiment of the present application. DETAILED DESCRIPTION

[0039] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0040] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0041] Figure 1 It is a structural diagram of a system architecture to which the intelligent monitoring and station operation and maintenance method in the embodiment of the present application can be applied.

[0042] See also Figure 1 The system architecture includes a sensor 110 , a processor 120 , a communication device 130 and a control unit 140 .

[0043] Sensor 110 includes a voltage sensor, a water flow sensor and a pressure sensor, and is the source of data for the entire system. Among them, the voltage sensor can measure the voltage data when the equipment is running; the water flow sensor is installed at a suitable position to measure the real-time water flow; the pressure sensor is installed at the water outlet to measure the water outlet pressure value. In other embodiments of the present application, the sensor may also include temperature sensors, water quality sensors, liquid level sensors and other types of sensors, which are not limited here.

[0044] As the core computing unit of the system, the processor 120 performs complex analysis, processing and calculation on the data after receiving various signal data from the sensor 110 and makes corresponding judgments and decisions.

[0045] The communication device 130 is responsible for establishing a channel for information transmission between various parts of the system, or between the system and external devices. It can send the data collected by the sensor 110 to the processor 120 for processing, and can also transmit the processing results or control instructions of the processor 120 to other related devices. At the same time, it can also exchange data with the outside world to ensure that the system can communicate with remote devices or personnel.

[0046] The control unit 140 performs corresponding actions according to the decision result of the processor 120. For example, when the processor determines that certain parameters are beyond the normal range and the device state needs to be adjusted, the control unit 140 will control the device according to the instructions, such as turning on or off the device, adjusting the operating parameters of the device, etc.

[0047] In related technologies, fault judgment of smart water management systems is mainly based on setting thresholds and comparing historical data. For the threshold setting method, the system sets reasonable upper and lower limits for key operating parameters such as water flow and pressure. When the monitored real-time data exceeds these preset ranges, a fault alarm is triggered. For the historical data comparison method, the system collects the equipment's past operating data and calculates reference values ​​such as average water flow and average pressure. By comparing the current real-time data with these historical reference data, when the deviation reaches a certain level, it is judged that the equipment may have a fault.

[0048] However, although this method can detect equipment failures to a certain extent, due to the complexity of the water system, fault judgment has certain limitations, and it is easy to make misjudgments or fail to accurately determine the type of fault.

[0049] By adopting the intelligent monitoring and station operation and maintenance method in the embodiment of the present application, by constructing an abnormal model, utilizing a fault type map and simulating fault types, integrating various data, analyzing the equipment operating conditions, and accurately classifying the abnormality level, the highly correlated fault type can be determined by calculating the correlation when warning of an abnormality, and the correctness of the fault type can be further confirmed through simulation comparison, thereby improving the accuracy of fault judgment and effectively reducing misjudgment.

[0050] Figure 2 It is a flow chart of the intelligent monitoring and station operation and maintenance method according to the embodiment of the present application, including the following steps:

[0051] S201, collecting real-time operation data of equipment;

[0052] Specifically, the real-time operation data includes real-time voltage data, real-time water flow data and real-time water flow outlet pressure data.

[0053] In order to obtain real-time operation data of the equipment, corresponding sensors will be installed at key parts of the equipment. The voltage sensor senses voltage fluctuations in real time and converts them into electrical signals to obtain real-time voltage data; the water flow sensor is installed in the water flow pipeline, and measures the water flow rate through electromagnetic induction, ultrasonic and other principles, and then calculates the real-time water flow data; the pressure sensor installed at the water outlet converts the pressure change into an electrical signal, and obtains the real-time water outlet pressure data after processing.

[0054] S202, combining the real-time operation data and the operation time data, obtaining an anomaly score according to an anomaly model, and classifying the anomaly levels;

[0055] Specifically, the anomaly model uses a preset machine learning algorithm, which is trained through a historical operation data group and its corresponding anomaly score; the anomaly level is divided into two levels: no anomaly and warning anomaly according to the anomaly score.

[0056] The collected real-time operation data, such as real-time voltage, water flow, and water outlet pressure data, are combined with the equipment operation time data. Then, these combined data are input into the trained anomaly model.

[0057] For this anomaly model, first of all, a large number of historical operation data sets of the equipment need to be collected. These data sets contain the operation data of the equipment at different time points in the past, such as voltage, water flow, water outlet pressure, etc., and also record the corresponding operation time of the equipment at that time. In addition, for each historical operation data set, there is an anomaly score marked by experts or based on actual fault conditions. These data constitute the historical operation data set and its corresponding anomaly score.

[0058] Select appropriate machine learning algorithms, such as support vector machines, random forests, etc., to train anomaly models.

[0059] In some embodiments of the present application, a random forest algorithm is used to construct multiple decision trees. During the training process, the historical operation data group with abnormal scores and its running time data are used as input, and these data are split and judged in each decision tree. The model continuously adjusts the nodes and branches of the decision tree by learning the rules in these data, so that the model can accurately predict the abnormal score according to the input features; in other embodiments of the present application, a support vector machine is used to first organize the historical operation data group and its corresponding abnormal score into a feature vector and standardize it. During training, a kernel function such as a Gaussian kernel function is selected to map the data to a high-dimensional space to process nonlinear relationships, and the preprocessed data and abnormal score labels are input into the model. The model adjusts the hyperplane parameters, uses optimization algorithms such as gradient descent and stochastic gradient descent, judges the category according to the input features, and continuously optimizes according to the difference between the predicted and actual labels, learns the data rules, and performs abnormal scoring when certain operation data feature combinations and running time meet specific conditions, which are not limited here.

[0060] Use a portion of the reserved historical operation data set and its corresponding anomaly score to verify the anomaly model, and evaluate the accuracy of the model by comparing the anomaly score predicted by the model with the actual anomaly score. If the accuracy does not meet the requirements, adjust the model parameters, such as the number and depth of trees in the random forest, or try other machine learning algorithms to train the model again until the model achieves satisfactory performance and obtains the anomaly model.

[0061] After the real-time operation data and the operation time data are input into the trained anomaly model, the model will calculate according to the previously learned rules. According to the pattern established during the training process, these features are comprehensively evaluated to output an anomaly score.

[0062] According to the pre-set abnormality scoring classification rules, if the abnormality score is higher than a certain threshold, it is a warning abnormality, and if it is lower than the threshold, it is no abnormality, the abnormality level of the device is divided.

[0063] S203, when the abnormality level is a warning abnormality, combining the real-time operation data and the equipment information, using the fault type map, calculating the correlation between the real-time operation data and the historical operation data corresponding to each fault type in the fault type map, and obtaining a fault type data group;

[0064] It can be understood that the fault type map is pre-constructed and includes historical operation data of various types of equipment and their corresponding fault types; the fault type data group includes all fault types and their corresponding correlations.

[0065] When the abnormality level is determined to be a warning abnormality, the current real-time operation data, together with the basic information of the equipment, such as model, specification, service life, etc., are compared with the pre-built fault type map. The fault type map stores a large amount of historical operation data of various types of equipment and the corresponding fault types.

[0066] Calculate the degree of correlation between real-time operation data and historical data under each fault type in the graph. First, extract the historical operation data corresponding to each fault type from the fault type graph. These historical operation data have the same feature dimensions as the real-time operation data, such as voltage, water flow, water outlet pressure, etc. At the same time, it is also necessary to clarify the equipment information, such as equipment model, age, manufacturer, etc., which may affect the relationship between the fault type and the operation data. For real-time operation data and historical operation data, feature engineering processing is performed to calculate the statistical characteristics of the data, such as mean, variance, rate of change, etc., which can better describe the distribution and changes of the data.

[0067] A variety of methods can be used to calculate the correlation. In some embodiments of the present application, the method for calculating the correlation is the Euclidean distance. For each fault type corresponding to the historical operation data and the real-time operation data, the Euclidean distance between them is calculated; in other embodiments of the present application, the method for calculating the correlation is the Pearson correlation coefficient, which measures the linear correlation between two variables. For each feature dimension of the historical operation data and the real-time operation data (such as voltage and voltage, water flow and water flow, etc.), the Pearson correlation coefficient is calculated, where and are the means of the historical operation data and the real-time operation data, respectively. The closer the correlation coefficient is to 1 or -1, the higher the correlation; the closer it is to 0, the lower the correlation; in other embodiments of the present application, the method for calculating the correlation can also use cosine similarity, treating the historical operation data and the real-time operation data as vectors, and calculating their cosine similarity. The value of cosine similarity is between [-1,1]. The closer it is to 1, the higher the correlation, indicating that the directions of the two vectors are closer, which is not limited here.

[0068] According to the selected correlation calculation method, the correlation between the real-time operation data and the historical operation data corresponding to each fault type in the fault type spectrum is calculated respectively. All fault types and their corresponding correlations are combined together to construct a fault type data group, and a fault type data group containing all fault types and their correlations is obtained.

[0069] S205, retrieve the operating parameters and layout information of the equipment, simulate the high-correlation fault type, and obtain real-time simulated operating data;

[0070] Specifically, the real-time simulation operation data includes simulation voltage data, simulation water flow data and simulation water flow outlet pressure data.

[0071] After determining the type of highly correlated fault, retrieve the equipment operating parameters (such as the rated voltage and designed water flow rate during normal operation) and layout information (such as the direction of the pipeline, equipment connection method, etc.). Based on this information, build a model that can reflect the actual operation of the equipment. The model can be a set of equations based on physical laws or an empirical model obtained through system identification and other methods, which can describe the dynamic and static relationship between various variables of the equipment under normal operation.

[0072] For different fault types, clarify how the fault type affects the equipment's operating parameters and physical structure. Each fault type has its own specific influencing factors. For example, a fault may cause a change in the parameters of a component (such as increased resistance and decreased capacitance), or change the characteristics of a fluid channel (such as pipe blockage and valve leakage). By adjusting the corresponding parameters in the model or changing part of the model's structure, we can simulate the scenario when a highly correlated fault occurs and finally obtain simulated operating data.

[0073] In some embodiments of the present application, a highly correlated fault type is a short circuit fault in a certain circuit part of a device. The circuit layout information of the device is known, including the connection method, resistance, capacitance and other parameters of each component. A circuit model that is the same as that of the device when it is operating normally is constructed. In the circuit model, the resistance value corresponding to the short circuit position is set to close to zero, thereby changing the flow path and size of the current. Through circuit analysis principles and related formulas, the analog voltage data of the device in this short circuit state, as well as the analog voltage, simulated water flow (if the circuit is related to water flow control) and simulated water flow outlet pressure data of other related parts that may be affected by the current change are calculated; in other embodiments of the present application, a highly correlated fault type is a partial blockage of a pipeline. According to the waterway layout information of the device, the diameter, length, material and other parameters of the pipeline are retrieved to construct a waterway layout model that is the same as that of the device when it is operating normally. In the waterway layout model, a specific position in the pipeline is selected, and the blockage is simulated by reducing the cross-sectional area of ​​the pipeline at that position. Using the principles of fluid mechanics, taking into account factors such as the viscosity of the water flow and pressure changes, the simulated water flow data of the equipment in the case of pipe blockage, as well as the upstream and downstream pressure changes caused by poor water flow, are calculated, and then the simulated water flow outlet pressure data is obtained, which is not limited here.

[0074] This step considers the impact mechanism of the fault on different operating parameters and the impact of the equipment layout on the fault, thereby verifying again whether the highly correlated fault type is the actual fault type.

[0075] S206: When the difference between the real-time simulation operation data and the real-time operation data is within a preset type judgment threshold range, determine that the real-time fault type is a high-correlation fault type.

[0076] Compare the real-time simulated operation data obtained by simulating highly correlated fault types with the real-time operation data actually collected by the equipment. For each data dimension, calculate the difference between them. Preset the threshold range for judging the fault type. When the difference between the simulated data and the real-time data in each dimension is within the preset threshold range, it indicates that the simulated fault scenario is highly consistent with the actual operation status of the equipment. The system thus determines that the real-time fault type of the current equipment is the highly correlated fault type.

[0077] In the above embodiment, by integrating various data and dividing the abnormality level, when the equipment is in the warning abnormal state, the correlation with various fault types can be calculated to determine the corresponding fault type with the highest correlation, and the fault type can be simulated by simulating the real-time equipment operation to verify whether the fault type judgment is correct. Compared with the related art, the fault type is judged only after the equipment fault is judged, and no further verification steps are performed. The intelligent monitoring and station operation and maintenance method provided by this application improves the accuracy of fault judgment.

[0078] In some embodiments, since there are many devices to be detected by the intelligent water monitoring station, multiple devices may be in the warning abnormal state at the same time in a short period of time. However, in this case, more important abnormal devices must be processed first to prevent serious consequences caused by slow processing of some dangerous abnormal situations. The intelligent monitoring and station operation and maintenance method can summarize and sort the abnormal scores of all devices in the warning abnormal state when they are in the warning abnormal state again, and summarize the abnormal score ranking of all devices in the warning abnormal state, so that users can more intuitively understand the abnormal importance of each warning abnormal device.

[0079] like Figure 3 FIG. 1 is another flow chart of the intelligent monitoring and station operation and maintenance method provided by the embodiment of the present application, which can be used for Figure 1 The system architecture shown includes the following steps:

[0080] S301, collecting real-time operation data of equipment;

[0081] S302, shutting down the device when the real-time voltage data is greater than a preset voltage threshold, the real-time water flow data is less than a preset water flow threshold, and the real-time water outlet pressure data is less than a preset water outlet pressure data threshold;

[0082] Real-time monitoring of the equipment's operating data, including voltage, water flow, and water outlet pressure. The acquired real-time voltage data is compared with the preset voltage threshold, and the real-time water flow data is compared with the preset water flow threshold, and the real-time water outlet pressure data is compared with the preset water outlet pressure data threshold. Once it is found that the real-time voltage data exceeds the preset upper limit, and the real-time water flow and water outlet pressure data are both lower than their respective preset lower limits, and when these three conditions are met at the same time, the system will immediately issue a command to cut off the power supply of the equipment through the control circuit, thereby realizing the shutdown operation of the equipment.

[0083] In this step, by shutting down the equipment in time when the real-time voltage data is too large, the real-time water flow data is too small, and the real-time water outlet pressure data is too small, problems such as circuit burning caused by excessive voltage, and equipment idling and mechanical parts wear caused by low water flow and pressure can be avoided, and operation can be stopped in time before the risk of serious damage may occur.

[0084] S303, combining the real-time operation data and the operation time data, obtaining an anomaly score according to an anomaly model, and classifying the anomaly levels;

[0085] S304, collecting upstream and downstream water level difference data of the equipment, and calculating theoretical water flow data;

[0086] The upstream and downstream water level difference data is obtained by subtracting the real-time data collected by the upstream and downstream water level sensors. The theoretical water flow data is calculated using the relevant formulas of fluid mechanics, combined with the known parameters such as the cross-sectional area and roughness of the pipeline, and the collected upstream and downstream water level difference data. This data represents the water flow that the equipment should have under the condition of real-time upstream and downstream water level difference under ideal conditions.

[0087] S305: if the difference between the theoretical water flow data and the real-time water flow data is greater than a preset water flow difference threshold, mark the real-time water flow data as suspicious data;

[0088] After calculating the theoretical water flow data, compare it with the real-time collected water flow data. Subtract the real-time water flow data from the theoretical water flow data to get the difference between the two, and compare the difference with the pre-set water flow difference threshold. If it is greater than the preset threshold, it means that the real-time water flow data deviates too much from the theoretical expectation. At this time, the real-time water flow data is marked as suspicious data, indicating that the data may be abnormal.

[0089] S306. When the abnormality level is no abnormality and the suspicious data exists, collect real-time sound characteristic data at the water outlet pipe of the equipment;

[0090] Specifically, the real-time sound feature data includes sound frequency distribution information and real-time sound intensity data.

[0091] When the system determines that the abnormality level of the equipment is normal, but detects suspicious real-time water flow data, it will start an additional detection process. At this time, a sound collection device, such as a microphone or acoustic sensor, will be installed at the water outlet pipe of the equipment. These devices start working, collecting sound signals from the water outlet pipe and analyzing and processing them. The sound frequency distribution information is extracted from it to understand the proportion of sounds of different frequencies, and the real-time sound intensity data is obtained at the same time to further understand the characteristics of the sound emitted when the equipment is running.

[0092] S307, calculating and obtaining an estimated value of the sound water flow rate by combining the real-time sound feature data, the first formula, the pipe inner diameter data and the pipe material data in the pipe material and size data;

[0093] Specifically, the first formula is: ; For the estimated value of the acoustic water flow, the pipe cross-sectional area , The comprehensive parameters related to the inner diameter of the pipe, pipe material and sound propagation characteristics , is the material data of the pipe. is a sound speed reference, is the standard deviation of the real-time sound frequency distribution in the real-time sound feature data, is the real-time sound intensity data in the real-time sound feature data, , To preset the coefficients related to sound intensity and water flow, is the correction coefficient function related to the frequency distribution.

[0094] In this first formula, : is the material data of the pipe. It is a sound speed reference used to standardize the sound speed of pipes of different materials. Pipes of different materials will have different effects on sound propagation, and this ratio can quantify this difference; is the standard deviation of the real-time sound frequency distribution in the real-time sound feature data, which describes the discrete degree of the sound frequency distribution. Different water flow states (such as laminar flow and turbulent flow) will produce different sound frequency distributions, and the standard deviation can reflect this difference; is in the frequency range Inside, about function The points here is a frequency distribution standard deviation Function constructed to describe the effect of frequency distribution on flow; assuming that the sound intensity With water flow There is a relationship between , the coefficients are obtained through experiments or theoretical derivation and , infer the water flow rate from the sound intensity, and transform the formula to get .

[0095] The first formula combines multiple factors that affect water flow (pipe size, sound intensity, and sound frequency distribution) to reflect the water flow state from multiple angles. Traditional estimates based only on sound intensity may not be accurate enough because it does not take into account the impact of water flow state. The first formula takes into account the water flow state (reflected by the sound frequency distribution) and the inherent characteristics of the pipe (through the pipe cross-sectional area and sound propagation characteristics), making the estimate more comprehensive. By introducing corrections to the sound velocity and frequency distribution related to the pipe material, the first formula can adapt to pipes of different materials and different operating conditions. Different pipe systems may produce different sound characteristics due to different materials. By quantifying different factors, the first formula can perform relatively accurate water flow estimates under different pipe systems and water flow conditions. The construction of the first formula is based on physical principles (such as area calculation, the relationship between sound propagation and water flow), and the parameters obtained through experimental fitting. and Ensure its reliability in practical applications.

[0096] S308: When the difference between the sound water flow estimation value and the real-time water flow data is greater than a preset water flow difference threshold, marking the corresponding device as a high-risk device;

[0097] After obtaining the sound water flow estimation value, the difference between it and the real-time water flow data is calculated. That is, the difference between the sound water flow estimation value and the real-time water flow data is subtracted, and the difference between the two is obtained. This difference is compared with the preset water flow difference threshold. If the difference is greater than the preset threshold, it indicates that there is a large deviation between the sound water flow estimation value and the real-time water flow data, which means that the equipment operation status may be seriously abnormal. At this time, the corresponding equipment is marked as a high-risk equipment.

[0098] S309: When the abnormality level is a warning abnormality, a warning signal is issued, and after deleting the old abnormality score of the device in the abnormality score data group, the abnormality score is stored in the abnormality score data group;

[0099] Specifically, the anomaly score data group includes the latest anomaly scores of multiple devices whose anomaly levels are warning anomalies; the old anomaly score is the anomaly score previously stored in the anomaly score data group for the device corresponding to the anomaly score.

[0100] When the system determines that the abnormality level of the device is a warning abnormality, first, the system will send a warning signal through the built-in communication module. This signal can be in the form of text messages, pop-up prompts, etc., to promptly notify the relevant operation and maintenance personnel of the abnormality of the equipment. Secondly, the system locates the old abnormality score previously stored in the abnormality score data group for the device and deletes it to ensure the timeliness of the data. Finally, the latest abnormality score calculated this time is stored in the abnormality score data group to ensure that the data group records the latest score of the warning abnormal device.

[0101] S310, sorting the data in the abnormal score data group from large to small, and marking the devices ranked within the top preset percentage threshold as high-risk devices;

[0102] After the system obtains the abnormal score data group, it will use a specific sorting algorithm, such as bubble sort or quick sort, to sort the data from large to small. After the sorting is completed, the number of devices to be selected is calculated based on the pre-set percentage threshold. For example, if the preset percentage threshold is 20%, and there are 100 devices with abnormal scores in the abnormal score data group, then the data of the first 20 devices will be selected and marked as high-risk devices.

[0103] If the device's current abnormality level is no abnormality, but it has previously experienced a warning abnormality, the abnormality score corresponding to the last warning abnormality will also be included in the ranking in the abnormality score data group to avoid ignoring the device that has experienced a fault when the device fails intermittently and is detected as normal in this time period but its fault has not been handled.

[0104] S311, send high-risk warning signals;

[0105] Specifically, the high-risk warning signal is a signal indicating that the high-risk equipment has a high-risk abnormality.

[0106] When the system completes marking high-risk equipment, it will start the signal sending mechanism. Through the built-in communication module, according to the pre-set communication protocol, the high-risk warning signal is sent to the designated receiving terminal.

[0107] This signal contains the identification information of high-risk devices in a specific coded form, as well as content indicating the existence of high-risk anomalies. For high-risk devices that rank high in the anomaly score data group, it also includes information such as their anomaly scores and anomaly score rankings.

[0108] The receiving terminal can be the operation and maintenance personnel’s mobile phone, computer monitoring platform, etc., to ensure that the operation and maintenance personnel can quickly receive this key information and know which equipment is in a high-risk state.

[0109] S312, when the abnormality level is a warning abnormality, combining the real-time operation data and the equipment information, using the fault type map, calculating the correlation between the real-time operation data and the historical operation data corresponding to each fault type in the fault type map, and obtaining a fault type data group;

[0110] S313, sorting the fault types in the fault type data group from high to low according to the correlation degree, and the fault type with the highest correlation degree is the high-correlation fault type;

[0111] S314, retrieve the operating parameters and layout information of the equipment, simulate the high-correlation fault type, and obtain real-time simulated operating data;

[0112] S315, determining whether the difference between the real-time simulation operation data and the real-time operation data is within a preset type determination threshold range;

[0113] If not, execute the following step S316;

[0114] If yes, execute the following step S317;

[0115] The real-time simulated operation data obtained by simulating the high-correlation fault type is compared with the real-time operation data actually collected by the equipment. The difference between the various indicators such as the simulated voltage data, simulated water flow data and simulated water outlet pressure data in the real-time simulated operation data and the corresponding real-time voltage data, real-time water flow data and real-time water outlet pressure data in the real-time operation data is calculated. Then, these differences are compared with the preset type judgment thresholds for each data type to determine whether the difference between the real-time simulated operation data and the real-time operation data is within the preset range. If it is not within the preset range, it is determined that the high-correlation fault type is not the actual fault type, and the following step S316 is executed to verify the next fault type according to the correlation ranking; if it is within the preset range, the real-time fault type is determined to be a high-correlation fault type.

[0116] S316, deleting the high-correlation fault type in the fault type data group, obtaining a new fault type ranking, the fault type with the highest ranking becomes the new high-correlation fault type, and executing the above step S314;

[0117] When the difference between the real-time simulation operation data and the real-time operation data is not within the preset type judgment threshold range, the system will delete the currently recognized high-correlation fault type from the fault type data group. After that, according to the original correlation sorting, the fault type with the highest correlation becomes the new high-correlation fault type. Then, according to the previously set process, the system will retrieve the equipment operation parameters and layout information again, simulate this new high-correlation fault type, generate real-time simulation operation data, and then determine again whether the difference between the newly generated real-time simulation operation data and the real-time operation data is within the preset range.

[0118] S317. Determine whether the real-time fault type is a high-correlation fault type.

[0119] Steps S301, S303, S312-S314, S317 and Figure 2 Steps S201 - S206 in the illustrated embodiment are similar, and the descriptions of steps S201 - S206 may be referred to, and will not be repeated here.

[0120] In the above embodiment, by collecting the real-time operation data of the equipment and combining the operation time data with the abnormal model to divide the abnormal level, the potential abnormality of the equipment can be discovered in time; when the abnormal level is a warning abnormality, the fault type is determined by the fault type map, and the real-time fault type is judged through simulation and comparison to achieve accurate fault diagnosis; at the same time, early warning signals are set at different links, high-risk equipment is marked, and the equipment is shut down when the data is abnormal. These steps enable the operation status of the equipment to be monitored in all directions, and equipment failures and their types are detected in a timely and accurate manner. When the real-time data is suspected of showing dangerous failure changes, the equipment is shut down in time to avoid production losses caused by equipment failures and ensure the stable operation of the measurement station.

[0121] The following introduces an exemplary intelligent monitoring and station operation and maintenance system 400 provided in an embodiment of the present application. Figure 4 It is a schematic diagram of an exemplary hardware structure of the intelligent monitoring and station operation and maintenance system 400 provided in an embodiment of the present application.

[0122] In some embodiments, the intelligent monitoring and station operation and maintenance system 400 includes a computer device. The computer device includes a processor, a memory and a network interface connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with other external terminals or servers through a network connection. In some embodiments, the network interface can be a wired network interface, and in some embodiments, the network interface can also be a wireless network interface. When the computer program is executed by the processor, the method in the embodiment of the present application is implemented.

[0123] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0124] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0125] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0126] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0127] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. An intelligent monitoring and station operation and maintenance method, characterized in that: The following steps are involved: Collecting real-time operation data of the equipment; the real-time operation data includes real-time voltage data, real-time water flow data and real-time water outlet pressure data; In combination with the real-time operation data and the operation time data, an abnormality score is obtained according to an abnormality model, and an abnormality level is divided; the abnormality model is obtained by training a historical operation data group and its corresponding abnormality score using a preset machine learning algorithm; the abnormality level is divided into two levels according to the abnormality score: no abnormality and warning abnormality; When the abnormality level is a warning abnormality, a warning signal is issued; the warning signal is a signal indicating that an abnormality exists in the current device; Collect the upstream and downstream water level difference data of the equipment and calculate the theoretical water flow data; When the difference between the theoretical water flow data and the real-time water flow data is greater than a preset water flow difference threshold, marking the real-time water flow data as suspicious data; When the abnormality level is no abnormality and the suspicious data exists, real-time sound characteristic data at the water outlet pipe of the equipment is collected; the real-time sound characteristic data includes sound frequency distribution information and real-time sound intensity data; Combining the real-time sound characteristic data with the pipe material and size data, calculating an estimated value of the sound water flow; When the difference between the acoustic water flow estimation value and the real-time water flow data is greater than a preset water flow difference threshold, marking the corresponding device as a high-risk device; In the case where the abnormality level is a warning abnormality, the real-time operation data and the equipment information are combined, and the fault type map is used to calculate the correlation between the real-time operation data and the historical operation data corresponding to each fault type in the fault type map, so as to obtain a fault type data group; the fault type map is pre-constructed and includes the historical operation data of various types of equipment and their corresponding fault types; the fault type data group includes all fault types and their corresponding correlations; Sorting the fault types in the fault type data group according to the correlation from high to low, the fault type with the highest correlation being the high-correlation fault type; Retrieving the operating parameters and layout information of the equipment, simulating the high-correlation fault type, and obtaining real-time simulated operating data; the real-time simulated operating data includes simulated voltage data, simulated water flow data, and simulated water flow outlet pressure data; When the difference between the real-time simulation operation data and the real-time operation data is within a preset type judgment threshold range, the real-time fault type is judged to be a high-correlation fault type.

2. The method according to claim 1, characterized in that When the abnormality level is a warning abnormality, issuing a warning signal specifically includes: In the case where the abnormality level is a warning abnormality, a warning signal is issued, and after deleting the old abnormality score of the device in the abnormality score data group, the abnormality score is stored in the abnormality score data group; the abnormality score data group includes the latest abnormality scores of multiple devices with the abnormality level being a warning abnormality; the old abnormality score is the abnormality score previously stored in the abnormality score data group for the device corresponding to the abnormality score; Sorting the data in the abnormal score data group from large to small, and marking the devices ranked within the top preset percentage threshold as high-risk devices; Send a high-risk warning signal; the high-risk warning signal is a signal that prompts the high-risk equipment to have a high-risk abnormality.

3. The method according to claim 1, characterized in that The step of combining the real-time sound characteristic data and the pipe material and size data to calculate the sound water flow estimation value specifically includes: The sound water flow estimation value is calculated by combining the real-time sound characteristic data, the first formula, the pipe inner diameter data and the pipe material data in the pipe material and size data; Among them, the first formula is: Q is the estimated value of the acoustic water flow, and the cross-sectional area of ​​the pipe d is the inner diameter of the pipe, a comprehensive parameter related to the pipe material and sound propagation characteristics v is the material data of the pipeline, c is a sound speed reference, σ f is the standard deviation of the real-time sound frequency distribution in the real-time sound feature data, I is the real-time sound intensity data in the real-time sound feature data, k and n are preset coefficients related to the sound intensity and water flow, and f(σ f ) is the correction coefficient function related to the frequency distribution.

4. The method according to claim 1, characterized in that: When the difference between the real-time simulated operation data and the real-time operation data is within the preset type judgment threshold range, after judging that the real-time fault type is a high-correlation fault type, the method further includes: when the difference between the simulated operation data and the real-time operation data is not within the preset type judgment threshold range, simulating all fault types in the fault type data group in sequence and calculating the simulated operation data; When the difference between the first simulation operation data and the real-time operation data is within a preset type judgment threshold range, the real-time fault type is judged to be the first fault type corresponding to the first simulation operation data.

5. The method according to claim 1, characterized in that After collecting the real-time operating data of the device, it also includes: shutting down the device when the real-time voltage data is greater than a preset voltage threshold, the real-time water flow data is less than a preset water flow threshold, and the real-time water outlet pressure data is less than a preset water outlet pressure data threshold.

6. An intelligent monitoring and station operation and maintenance system, characterized in that: The intelligent monitoring and station operation and maintenance system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent monitoring and station operation and maintenance system to execute the method described in any one of claims 1-5.

7. A computer program product comprising instructions, characterized in that When the computer program product runs on an intelligent monitoring and station operation and maintenance system, the intelligent monitoring and station operation and maintenance system is enabled to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the intelligent monitoring and station operation and maintenance system, the intelligent monitoring and station operation and maintenance system executes the method as described in any one of claims 1 to 5.

Images