Electric furnace equipment intelligent operation and maintenance management system based on gateway data acquisition

Abstract

The invention discloses an electric furnace equipment intelligent operation and maintenance management system based on gateway data acquisition, which relates to the technical field of electric furnace equipment intelligent operation and maintenance management and comprises a data acquisition module, a transmission process division module, a real-time monitoring module, a hidden danger classification module and a response measure module. The data acquisition module is used for acquiring current data of each branch circuit in real time through current sensors arranged on the branch circuits of the induction furnace and transmitting the acquired current data to the central system through the gateway; and a transmission process division module. The current sensor is arranged to collect current data of the induction furnace and transmit the current data to the central system through the gateway, refined monitoring and intelligent hidden danger detection are achieved, timely early warning and data loss prevention are achieved, system reliability and response speed are improved, after data loss hidden dangers are detected, the hidden dangers are comprehensively analyzed and classified, and corresponding measures are taken, so that the safety of a system is improved. Problems are accurately solved, operation of the induction furnace is optimized, the service life of equipment is prolonged, and production efficiency and product quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent operation and maintenance management of electric furnace equipment, and in particular to an intelligent operation and maintenance management system of electric furnace equipment based on gateway data collection. Background Art

[0002] Intelligent operation and maintenance management of electric furnace equipment based on gateway data collection is a method of intelligent management of electric furnace equipment using the Internet of Things and big data technology. First of all, the gateway is a central node that connects various devices and sensors, through which data collection and transmission can be realized. As a high-energy-consuming and complex industrial equipment, the electric furnace will generate a large amount of data during operation, including parameters such as temperature, pressure, current, and voltage. Through various sensors deployed on the electric furnace, these parameters are monitored in real time, and the data is transmitted to the cloud or local centralized management system through the gateway. The gateway can not only realize seamless data collection, but also has preliminary data processing capabilities, which can filter, aggregate and preprocess data, thereby reducing the transmission of invalid data and improving the efficiency and reliability of data transmission.

[0003] With the support of these basic data, the intelligent operation and maintenance management system can conduct comprehensive and real-time monitoring and analysis of the operation status of the electric furnace. Through the comprehensive analysis of historical data and real-time data, the system can identify the operation rules of the equipment, discover potential hidden faults, and issue early warnings. For example, if the temperature of a component continues to be higher than the normal value, the system will issue an alarm to prompt the operation and maintenance personnel to conduct inspections and maintenance. In addition, the intelligent operation and maintenance management system can also formulate optimized maintenance strategies based on the operating status of the equipment, reduce unnecessary downtime and maintenance time, and improve equipment utilization and production efficiency. Through these intelligent means, not only can the service life of electric furnace equipment be extended and maintenance costs reduced, but also the safety and reliability of production can be improved, and ultimately the efficient and intelligent management of electric furnace equipment can be achieved.

[0004] Intelligent operation and maintenance management of electric furnace equipment based on gateway data collection is also applicable to induction furnaces, because induction furnaces require precise current and temperature control during operation to ensure the stability and efficiency of the melting and heating processes. By collecting various sensor data of the induction furnace (such as current, voltage, temperature, etc.) through the gateway, real-time monitoring, fault warning and maintenance optimization can be achieved, thereby improving equipment operation efficiency, extending equipment life, reducing downtime, and ensuring production quality and safety. Therefore, as an important electric furnace equipment, intelligent operation and maintenance management is of great significance to induction furnaces.

[0005] The prior art has the following deficiencies: When performing intelligent operation and maintenance management of the induction furnace in the electric furnace equipment based on gateway data collection, it is very important to obtain the branch current data of the induction furnace. If these current data fail to be successfully transmitted to the central system through the gateway, resulting in the loss of some current data, and the existing technology fails to detect the problem in time, the operation and maintenance system will not be able to detect and adjust the current in time. This may cause the induction furnace to operate at too high or too low current. Excessive current may cause the induction coil to overheat, the insulation layer to be damaged, and even cause arc faults, which will seriously damage the equipment; too low current may cause incomplete melting process and affect product quality.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an intelligent operation and maintenance management system for electric furnace equipment based on gateway data acquisition. By deploying current sensors to collect induction furnace branch current data in real time, and transmitting it to the central system through the gateway, detailed monitoring and intelligent hidden danger detection can be achieved, and early warning and data loss can be prevented in time to improve system reliability and response speed. After detecting the hidden danger of data missing, the data transmission situation is comprehensively analyzed, and the hidden dangers are divided into accidental occurrence type, intermittent occurrence type and continuous occurrence type, and different response measures are taken to accurately identify and solve the problems, optimize the operation of the induction furnace, extend the life of the induction furnace, and improve production efficiency and product quality to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent operation and maintenance management system for electric furnace equipment based on gateway data acquisition, comprising a data acquisition module, a transmission process division module, a real-time monitoring module, a hidden danger classification module and a countermeasures module; The data acquisition module collects the current data of each branch in real time through the current sensors deployed on the branches of the induction furnace, and transmits the collected current data to the central system through the gateway; The transmission process division module divides the transmission process of current data into several sub-periods of fixed duration to refine data monitoring; Real-time monitoring module, establishes a real-time monitoring mechanism for current data transmission, monitors the current data transmission status in each sub-period, and intelligently detects the hidden danger of data loss when current data is transmitted through the gateway; The hidden danger classification module, when detecting the hidden danger of data loss in current data transmission, obtains the current data transmission situation of several sub-periods for comprehensive analysis, and divides the hidden danger of data loss into accidental occurrence type, intermittent occurrence type and continuous occurrence type; The countermeasures module adopts different types of countermeasures for accidental, intermittent and continuous data loss risks.

[0009] Preferably, in each sub-period, the usage of the gateway cache area and the proportion of data packets lost during the data transmission process are obtained when current data is transmitted through the gateway. After the acquisition, the gateway cache area usage and the proportion of data packets lost during the data transmission process are analyzed and processed for abnormalities, and a gateway cache overflow index and a data packet loss rate floating index are generated.

[0010] Preferably, the gateway cache overflow index and the data packet loss rate floating index are input into a pre-trained machine learning model, and a data missing assessment coefficient is generated based on the machine learning model. The current data transmission situation in each sub-period is monitored by the data missing assessment coefficient, and the hidden danger of data missing when current data is transmitted through the gateway is intelligently detected.

[0011] Preferably, the data missing assessment coefficient generated in each sub-period when the current data is transmitted through the gateway is compared and analyzed with a preset data missing assessment coefficient reference threshold, so as to intelligently detect the hidden danger of data missing when the current data is transmitted through the gateway. The specific process is as follows: If the data missing assessment coefficient is greater than or equal to the data missing assessment coefficient reference threshold, the transmission of current data through the gateway in the sub-period is classified as a data missing hidden danger period, indicating that there is a hidden danger of data missing when the current data is transmitted through the gateway; If the data missing assessment coefficient is less than the data missing assessment coefficient reference threshold, the transmission of current data through the gateway in the sub-period is classified as an efficient transmission period, indicating that efficient transmission can be achieved when current data is transmitted through the gateway.

[0012] Preferably, when it is detected that there is a risk of data missing in the transmission of current data, that is, when there is a period of data missing risk in the transmission of current data through the gateway, the data missing assessment coefficients generated during the current data transmission in several subsequent sub-periods are obtained to establish a data set, and the current data transmission situation is comprehensively analyzed through the several data missing assessment coefficients in the data set.

[0013] Preferably, the data missing assessment coefficient standard deviation and the data missing assessment coefficient mean value are calculated by the data missing assessment coefficient in the data set, and the data missing assessment coefficient standard deviation and the data missing assessment coefficient mean value are respectively compared and analyzed with a preset standard deviation reference threshold and a preset data missing assessment coefficient reference threshold, and the data missing hidden dangers are divided. The results of the comparison and analysis are as follows: If the average value of the data missing assessment coefficient is greater than or equal to the reference threshold of the data missing assessment coefficient, the data missing risk is classified as a continuous occurrence type; If the mean value of the data missing assessment coefficient is less than the reference threshold of the data missing assessment coefficient and the standard deviation of the data missing assessment coefficient is greater than or equal to the reference threshold of the standard deviation, the data missing risk is classified as intermittent occurrence type; If the mean value of the data missing assessment coefficient is less than the reference threshold of the data missing assessment coefficient and the standard deviation of the data missing assessment coefficient is less than the reference threshold of the standard deviation, the data missing risk is classified as accidental.

[0014] Preferably, for persistent data loss risks, immediate in-depth investigation and repair are required to prevent larger equipment failures or safety accidents; For intermittent data loss risks, identify and resolve the root causes through detailed monitoring and analysis; For accidental data loss risks, attention should be paid and recorded to prevent accidental problems from developing into more serious intermittent or continuous problems, and the probability of occurrence should be reduced by optimizing network configuration and equipment maintenance.

[0015] Preferably, in each sub-period, after performing abnormal analysis on the usage of the gateway cache area, the steps of generating the gateway cache overflow index are as follows: In each sub-period, the usage data of the gateway cache is collected, including: the usage of the gateway cache at time t , the maximum capacity of the gateway cache ; Calculate the usage of the gateway cache in each sub-period. The calculation expression is: , where Indicates the cache usage at time t, ranging from [0, 1]; In each sub-period, detect whether the gateway cache overflows and record the number of overflow events. The detection expression is: ,in, E is the total number of buffer overflow events that occurred during the subperiod, represents the indicator function, if ,but ,otherwise , N Indicates the number of time sampling points in the sub-period; Calculate the gateway cache overflow index in each sub-period, taking into account the cache usage rate and the number of overflow events. The calculation expression is: , where Indicates the gateway cache overflow index, Indicates the average cache usage in the sub-period. Indicates the frequency of buffer overflow events in the sub-period, Indicates the extent to which the cache usage rate deviates from the normal range, indicating the degree of fluctuation in cache usage. T Indicates the total duration of the sub-period. , , They represent the average cache usage, the frequency of cache overflow events, and the weight of the cache usage deviation from the normal range.

[0016] Preferably, in each sub-period, after performing abnormal analysis on the proportion of data packets lost during data transmission, the steps of generating a data packet loss rate floating index are as follows: In each sub-period, get the total number of packets expected to be transmitted , the actual number of packets lost And the baseline loss rate ,The baseline loss rate is the packet loss rate under an ideal ,situation, which is used to evaluate the change of the actual loss rate; Calculate the actual loss rate, the calculation expression is: , Indicates the actual loss rate; Calculate the loss rate change value. The loss rate change value is defined as the change in the actual loss rate relative to the baseline loss rate. The calculation expression is: , where Indicates the change value of loss rate; Smooth the change in loss rate. The smoothing expression is: , where Indicates the smoothed loss rate change value of the current period Indicates the change value of the smoothed loss rate in the previous period, It represents the change value of loss rate after smoothing. represents the smoothing factor, ; Calculate the floating index of packet loss rate. The calculation expression is: , where Indicates the floating index of packet loss rate. Indicates the base value for normalization calculations.

[0017] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention collects current data of each branch in real time by deploying current sensors on the branches of the induction furnace, and transmits the data to the central system through the gateway, so as to realize detailed monitoring of the current data. In each sub-period, the usage of the gateway buffer area and the data packet loss ratio are monitored, and a gateway buffer overflow index and a data packet loss rate floating index are generated. These indicators are input into a pre-trained machine learning model to generate a data missing assessment coefficient. The data missing assessment coefficient can be used to intelligently detect hidden dangers in data transmission, ensure the real-time and integrity of the current data, timely discover and warn problems in data transmission, and prevent data loss, thereby improving the reliability and response speed of the entire system.

[0018] After detecting the existence of data missing risks in current data transmission, the present invention divides the data missing risks into accidental, intermittent and continuous types through comprehensive analysis of the data transmission conditions in several sub-periods, and takes corresponding countermeasures according to different types of data missing risks. This classification and response strategy can not only accurately identify the nature and severity of the problem, but also carry out targeted maintenance and optimization to avoid blind operation. By providing accurate data and analysis results, operation and maintenance personnel can make decisions more effectively, optimize the operation of the induction furnace, extend the life of the induction furnace, and ultimately improve production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a module schematic diagram of the intelligent operation and maintenance management system of electric furnace equipment based on gateway data collection of the present invention. DETAILED DESCRIPTION

[0021] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0022] The present invention provides Figure 1 The electric furnace equipment intelligent operation and maintenance management system based on gateway data acquisition shown includes a data acquisition module, a transmission process division module, a real-time monitoring module, a hidden danger classification module and a response measure module; The data acquisition module collects the current data of each branch in real time through the current sensors deployed on the branches of the induction furnace, and transmits the collected current data to the central system through the gateway; Current sensors are special devices installed on each branch of the induction furnace to measure the current value passing through the branch in real time. These sensors can accurately capture the instantaneous changes in current and convert the collected current data into signals that can be transmitted. These signals are transmitted to the central system through the gateway for further monitoring and analysis, ensuring that the current data of the induction furnace in operation is recorded and monitored in real time and accurately; These sensors should have high precision and high response speed to ensure the accuracy and timeliness of the data. The collected current data includes multiple parameters such as instantaneous current value and average current value to fully reflect the working status of the induction furnace. This step is the basis to ensure that the original data for subsequent data processing and transmission is reliable.

[0023] The transmission process division module divides the transmission process of current data into several sub-periods of fixed duration to refine data monitoring; The entire transmission process is divided into several sub-periods of fixed length, for example, every 5 minutes is a sub-period. The purpose of this is to refine data monitoring so that the data transmission situation in each period can be analyzed and monitored separately. This division method helps to accurately locate any problems that occur during the data transmission process.

[0024] Real-time monitoring module, establishes a real-time monitoring mechanism for current data transmission, monitors the current data transmission status in each sub-period, and intelligently detects the hidden danger of data loss when current data is transmitted through the gateway; In each sub-period, the gateway buffer usage and the proportion of data packets lost during the data transmission process are obtained when the current data is transmitted through the gateway. After obtaining, the gateway buffer usage and the proportion of data packets lost during the data transmission process are analyzed and processed abnormally to generate the gateway buffer overflow index and the data packet loss rate floating index; The gateway cache overflow index and the packet loss rate floating index are input into the pre-trained machine learning model, and a data missing assessment coefficient is generated based on the machine learning model. The current data transmission situation in each sub-period is monitored by the data missing assessment coefficient, and the data missing risk when the current data is transmitted through the gateway is intelligently detected; When current data is transmitted through the gateway, a gateway cache overflow will cause current data to be missing when the current data is transmitted through the gateway. Specifically, when the gateway receives data from the current sensor, it will temporarily store the data in the cache, waiting for further processing and transmission. If the cache space is full due to excessive data volume, insufficient processing speed or other reasons, new data packets will not be able to be stored in the cache, but will be directly discarded. In this case, some current data will not be successfully transmitted to the central system, resulting in data loss, which in turn affects the system's real-time monitoring and accurate judgment of the operating status of the induction furnace. Therefore, the overflow of the gateway cache directly leads to the loss of current data during the transmission process, seriously affecting the reliability and effectiveness of the intelligent operation and maintenance management system.

[0025] In each sub-period, after analyzing the abnormality of the gateway cache usage, the steps to generate the gateway cache overflow index are as follows: In each sub-period, the usage data of the gateway cache is collected, including: the usage of the gateway cache at time t , the maximum capacity of the gateway cache ; Calculate the usage of the gateway cache in each sub-period. The calculation expression is: , where Indicates the cache usage at time t, ranging from [0, 1]; In each sub-period, detect whether the gateway cache overflows and record the number of overflow events. The detection expression is: ,in, E is the total number of buffer overflow events that occurred during the subperiod, represents the indicator function, if ,but ,otherwise , N Indicates the number of time sampling points in the sub-period; Calculate the gateway cache overflow index in each sub-period, taking into account the cache usage rate and the number of overflow events. The calculation expression is: , where Indicates the gateway cache overflow index, Indicates the average cache usage in the sub-period. Indicates the frequency of buffer overflow events in the sub-period, Indicates the extent to which the cache usage rate deviates from the normal range, indicating the degree of fluctuation in cache usage. T Indicates the total duration of the sub-period. , , They represent the average cache usage, the frequency of cache overflow events, and the weight of the cache usage deviation from the normal range. , , Without making any specific restrictions here, the criteria are set based on weighing the importance of the average cache usage, the frequency of cache overflow events, and the deviation of the cache usage from the normal range. Specifically, Reflects the impact of the average cache usage on system stability. Its weight is high (such as 0.5) because a sustained high usage may indicate potential cache insufficiency. Reflects the frequency of cache overflow events, with a moderate weight (such as 0.3) because overflow events directly lead to data loss. Reflects the fluctuation of cache usage. Its weight is relatively low (such as 0.2), but it still needs attention because sharp fluctuations may indicate sudden problems. The specific value of the weight should be adjusted based on historical data analysis and actual operation and maintenance experience to optimize the accuracy and response capability of system warnings.

[0026] It can be seen from the gateway cache overflow index that in each sub-period, the larger the performance value of the gateway cache overflow index generated after analyzing the usage of the gateway cache area and handling the exceptions, the greater the hidden danger of current data loss when the current data is transmitted through the gateway. On the contrary, if the performance value of the gateway cache overflow index is smaller, it indicates that the hidden danger of data loss when the current data is transmitted through the gateway is smaller. This is because a larger gateway cache overflow index usually reflects a higher cache usage rate, frequent overflow events, and significant usage fluctuations, indicating that the gateway cache is under high load or unstable state, increasing the risk of data loss.

[0027] When current data is transmitted through a gateway, if the proportion of data packets lost during the data transmission process is high, data loss will occur when the current data is transmitted through the gateway. This is because during the data transmission process, each data packet contains key information such as the specific measurement value and timestamp of the current. If the packet loss rate is high, a large number of current measurements cannot reach the central system, resulting in the monitoring system being unable to obtain a complete current data sequence. Missing data packets mean that the continuity of current data is interrupted, affecting real-time monitoring, historical data analysis, and accurate assessment of equipment status. In this case, the operation and maintenance system will not be able to accurately monitor and predict the changing trend of the current, which may result in the failure to detect equipment abnormalities in a timely manner, thereby increasing the risk of equipment operation and affecting production efficiency and equipment life. Therefore, ensuring a low packet loss rate is critical to maintaining the integrity and reliability of current data transmission.

[0028] In each sub-period, after abnormal analysis of the proportion of data packets lost during data transmission, the steps to generate the data packet loss rate floating index are as follows: In each sub-period, get the total number of packets expected to be transmitted , the actual number of packets lost And the baseline loss rate ,The baseline loss rate is the packet loss rate under an ideal ,situation, which is used to evaluate the change of the actual loss rate; The baseline loss rate can be obtained by analyzing historical data. Specifically, when the device and network are operating normally, data packet transmission records can be collected over a period of time, and the average data packet loss rate during this period can be calculated as the baseline loss rate. This method takes advantage of the stability and representativeness of historical data and can provide a reference standard for changes in actual loss rates.

[0029] Calculate the actual loss rate, the calculation expression is: , Indicates the actual loss rate; Calculate the loss rate change value. The loss rate change value is defined as the change in the actual loss rate relative to the baseline loss rate. The calculation expression is: , where Indicates the change value of loss rate; Smooth the change in loss rate. The smoothing expression is: , where Indicates the smoothed loss rate change value of the current period Indicates the change value of the smoothed loss rate in the previous period, It represents the change value of loss rate after smoothing. represents the smoothing factor, ; The purpose of smoothing the loss rate change is to reduce the impact of short-term fluctuations on data analysis, making the loss rate change more stable and reliable, thereby reflecting longer-term trends and abnormal situations. This helps the intelligent operation and maintenance system to more accurately identify and predict potential problems in data transmission and improve the system's early warning and response capabilities.

[0030] Calculate the floating index of packet loss rate. The calculation expression is: , where Indicates the floating index of packet loss rate. It indicates the benchmark value for standardized calculation to ensure that the calculation result is within a reasonable range.

[0031] It can be seen from the data packet loss rate floating index that in each sub-period, the larger the performance value of the data packet loss rate floating index generated after abnormal analysis of the proportion of data packets lost during data transmission, the higher the proportion of data packets lost when the current data is transmitted through the gateway in each sub-period, which means that the hidden danger of current data loss is greater. Conversely, if the performance value of the data packet loss rate floating index is smaller, it means that the proportion of data packet loss is lower, the current data transmission is more stable, and the hidden danger of data loss is relatively small. By quantifying the rising trend of the loss rate, it helps the intelligent operation and maintenance system to better monitor and predict potential problems in data transmission.

[0032] The machine learning model is not specifically limited here, and can achieve the gateway cache overflow index and packet loss rate floating index Perform comprehensive analysis to generate missing data assessment coefficients In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; Missing data estimation coefficient The resulting calculation formula is: , where , Gateway Cache Overflow Index and packet loss rate floating index The preset scaling factor of , Both are greater than 0.

[0033] It can be seen from the data missing assessment coefficient that in each sub-period, the larger the performance value of the gateway cache overflow index generated after analyzing the usage of the gateway cache area and handling the exception, the larger the performance value of the packet loss rate floating index generated after performing the exception analysis and processing on the proportion of data packets lost during data transmission, that is, the larger the performance value of the data missing assessment coefficient generated in each sub-period, the greater the hidden danger of current data missing when the current data is transmitted through the gateway, and vice versa.

[0034] The data missing assessment coefficient generated in each sub-period when the current data is transmitted through the gateway is compared and analyzed with the pre-set data missing assessment coefficient reference threshold, so as to intelligently detect the data missing risk when the current data is transmitted through the gateway. The specific process is as follows: If the data missing assessment coefficient is greater than or equal to the data missing assessment coefficient reference threshold, the transmission of current data through the gateway in the sub-period is classified as a data missing hidden danger period, indicating that there is a hidden danger of data missing when the current data is transmitted through the gateway; If the data missing assessment coefficient is less than the data missing assessment coefficient reference threshold, the transmission of current data through the gateway in the sub-period is classified as an efficient transmission period, indicating that efficient transmission can be achieved when current data is transmitted through the gateway.

[0035] The hidden danger classification module, when detecting the hidden danger of data loss in current data transmission, obtains the current data transmission situation of several sub-periods for comprehensive analysis, and divides the hidden danger of data loss into accidental occurrence type, intermittent occurrence type and continuous occurrence type; When it is detected that there is a risk of data missing in the transmission of current data, that is, when there is a period of data missing risk in the transmission of current data through the gateway, the data missing assessment coefficients generated during the current data transmission in subsequent sub-periods are obtained to establish a data set, and the current data transmission situation is comprehensively analyzed through the several data missing assessment coefficients in the data set.

[0036] The standard deviation and the average value of the missing data assessment coefficient are calculated through the missing data assessment coefficient in the data set, and the standard deviation and the average value of the missing data assessment coefficient are compared and analyzed with the preset standard deviation reference threshold and the preset data missing assessment coefficient reference threshold respectively, and the data missing risks are divided. The results of the comparison and analysis are as follows: If the average value of the data missing assessment coefficient is greater than or equal to the reference threshold of the data missing assessment coefficient, the data missing risk is classified as a continuous occurrence type; If the mean value of the data missing assessment coefficient is less than the reference threshold of the data missing assessment coefficient and the standard deviation of the data missing assessment coefficient is greater than or equal to the reference threshold of the standard deviation, the data missing risk is classified as intermittent occurrence type; If the mean value of the data missing assessment coefficient is less than the reference threshold of the data missing assessment coefficient and the standard deviation of the data missing assessment coefficient is less than the reference threshold of the standard deviation, the data missing risk is classified as accidental.

[0037] The countermeasures module takes different types of countermeasures for accidental, intermittent and continuous data loss risks; The persistent data loss risk means that the current data is continuously and stably missing during the data transmission process. This usually means that there is a long-term or permanent transmission problem, such as hardware failure, serious network problems, or persistent electromagnetic interference. Since this risk persists, it may seriously affect the operation of the system and the integrity of the data, resulting in the inability of the operation and maintenance system to reliably monitor and control the equipment. Persistent risks require immediate in-depth investigation and repair to prevent larger equipment failures or safety accidents.

[0038] Intermittent data loss means that the current data loss occurs intermittently in data transmission, and the frequency and pattern have certain fluctuations. This is usually caused by network congestion, temporary interference or intermittent equipment failure. Although this risk is not as serious as the continuous type, it will cause unstable data transmission and affect the real-time and reliability of the operation and maintenance system. Intermittent data loss may mask some potential equipment problems, which require detailed monitoring and analysis to identify and solve the root cause.

[0039] The accidental data loss hazard means that during the data transmission process, the current data loss is accidental, and the missing events are rare and have no obvious regularity. This is usually caused by temporary network fluctuations, short-term equipment abnormalities, or occasional environmental interference. Although this type of hazard has a small overall impact on the system, it still needs to be paid attention to and recorded to prevent accidental problems from developing into more serious intermittent or continuous problems. For accidental hazards, their probability of occurrence can be reduced by optimizing network configuration and equipment maintenance.

[0040] The present invention collects current data of each branch in real time by deploying current sensors on the branches of the induction furnace, and transmits the data to the central system through the gateway, so as to realize detailed monitoring of the current data. In each sub-period, the usage of the gateway buffer area and the data packet loss ratio are monitored, and a gateway buffer overflow index and a data packet loss rate floating index are generated. These indicators are input into a pre-trained machine learning model to generate a data missing assessment coefficient. The data missing assessment coefficient can be used to intelligently detect hidden dangers in data transmission, ensure the real-time and integrity of the current data, timely discover and warn problems in data transmission, and prevent data loss, thereby improving the reliability and response speed of the entire system.

[0041] After detecting the existence of data missing risks in current data transmission, the present invention divides the data missing risks into accidental, intermittent and continuous types through comprehensive analysis of the data transmission conditions in several sub-periods, and takes corresponding countermeasures according to different types of data missing risks. This classification and response strategy can not only accurately identify the nature and severity of the problem, but also carry out targeted maintenance and optimization to avoid blind operation. By providing accurate data and analysis results, operation and maintenance personnel can make decisions more effectively, optimize the operation of the induction furnace, extend the life of the induction furnace, and ultimately improve production efficiency and product quality.

[0042] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0043] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments 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 or computer programs. When the computer instructions or computer programs are loaded or 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 can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can 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 can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0044] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0045] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0046] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0047] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0048] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0049] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Intelligent operation and maintenance management system for electric furnace equipment based on gateway data collection, characterized in that: It includes data acquisition module, transmission process division module, real-time monitoring module, hidden danger classification module and response measures module; The data acquisition module collects the current data of each branch in real time through the current sensors deployed on the branches of the induction furnace, and transmits the collected current data to the central system through the gateway; The transmission process division module divides the transmission process of current data into several sub-periods of fixed duration to refine data monitoring; Real-time monitoring module, establishes a real-time monitoring mechanism for current data transmission, monitors the current data transmission status in each sub-period, and intelligently detects the hidden danger of data loss when current data is transmitted through the gateway; The hidden danger classification module, when detecting the hidden danger of data loss in current data transmission, obtains the current data transmission situation of several sub-periods for comprehensive analysis, and divides the hidden danger of data loss into accidental occurrence type, intermittent occurrence type and continuous occurrence type; The countermeasures module adopts different types of countermeasures for accidental, intermittent and continuous data loss risks.

2. The intelligent operation and maintenance management system for electric furnace equipment based on gateway data acquisition according to claim 1 is characterized in that: In each sub-period, the gateway cache usage and the proportion of data packets lost during the data transmission process are obtained when current data is transmitted through the gateway. After obtaining, the gateway cache usage and the proportion of data packets lost during the data transmission process are analyzed and processed for abnormalities, and the gateway cache overflow index and the data packet loss rate floating index are generated.

3. The intelligent operation and maintenance management system for electric furnace equipment based on gateway data acquisition according to claim 2 is characterized in that: The gateway cache overflow index and the packet loss rate floating index are input into the pre-trained machine learning model, and a data missing assessment coefficient is generated based on the machine learning model. The current data transmission situation in each sub-period is monitored by the data missing assessment coefficient, and the hidden danger of data missing when current data is transmitted through the gateway is intelligently detected.

4. The intelligent operation and maintenance management system for electric furnace equipment based on gateway data acquisition according to claim 3 is characterized in that: The data missing assessment coefficient generated in each sub-period when the current data is transmitted through the gateway is compared and analyzed with the pre-set data missing assessment coefficient reference threshold, so as to intelligently detect the data missing risk when the current data is transmitted through the gateway. The specific process is as follows: If the data missing assessment coefficient is greater than or equal to the data missing assessment coefficient reference threshold, the transmission of current data through the gateway in the sub-period is classified as a data missing hidden danger period, indicating that there is a hidden danger of data missing when the current data is transmitted through the gateway; If the data missing assessment coefficient is less than the data missing assessment coefficient reference threshold, the transmission of current data through the gateway in the sub-period is classified as an efficient transmission period, indicating that efficient transmission can be achieved when current data is transmitted through the gateway.

5. The intelligent operation and maintenance management system for electric furnace equipment based on gateway data collection according to claim 4 is characterized in that: When it is detected that there is a risk of data missing in the transmission of current data, that is, when there is a period of data missing risk in the transmission of current data through the gateway, the data missing assessment coefficients generated during the current data transmission in subsequent sub-periods are obtained to establish a data set, and the current data transmission situation is comprehensively analyzed through the several data missing assessment coefficients in the data set.

6. The intelligent operation and maintenance management system for electric furnace equipment based on gateway data collection according to claim 5 is characterized in that: The standard deviation and the average value of the missing data assessment coefficient are calculated through the missing data assessment coefficient in the data set, and the standard deviation and the average value of the missing data assessment coefficient are compared and analyzed with the preset standard deviation reference threshold and the preset data missing assessment coefficient reference threshold respectively, and the data missing risks are divided. The results of the comparison and analysis are as follows: If the average value of the data missing assessment coefficient is greater than or equal to the reference threshold of the data missing assessment coefficient, the data missing risk is classified as a continuous occurrence type; If the mean value of the data missing assessment coefficient is less than the reference threshold of the data missing assessment coefficient and the standard deviation of the data missing assessment coefficient is greater than or equal to the reference threshold of the standard deviation, the data missing risk is classified as intermittent occurrence type; If the mean value of the data missing assessment coefficient is less than the reference threshold of the data missing assessment coefficient and the standard deviation of the data missing assessment coefficient is less than the reference threshold of the standard deviation, the data missing risk is classified as accidental.

7. The intelligent operation and maintenance management system for electric furnace equipment based on gateway data collection according to claim 1 is characterized in that: For persistent data loss risks, immediate in-depth investigation and repair are required to prevent larger equipment failures or safety incidents. For intermittent data loss risks, identify and resolve the root causes through detailed monitoring and analysis; For accidental data loss risks, attention should be paid and recorded to prevent accidental problems from developing into more serious intermittent or continuous problems, and the probability of occurrence should be reduced by optimizing network configuration and equipment maintenance.

8. The intelligent operation and maintenance management system for electric furnace equipment based on gateway data collection according to claim 3 is characterized in that: In each sub-period, after analyzing the abnormality of the gateway cache usage, the steps to generate the gateway cache overflow index are as follows: In each sub-period, the usage data of the gateway cache is collected, including: the usage of the gateway cache at time t , the maximum capacity of the gateway cache ; Calculate the usage of the gateway cache in each sub-period. The calculation expression is: , where Indicates the cache usage at time t, ranging from [0, 1]; In each sub-period, detect whether the gateway cache overflows and record the number of overflow events. The detection expression is: ,in, E is the total number of buffer overflow events that occurred during the subperiod, represents the indicator function, if ,but ,otherwise , N Indicates the number of time sampling points in the sub-period; Calculate the gateway cache overflow index in each sub-period, taking into account the cache usage rate and the number of overflow events. The calculation expression is: , where Indicates the gateway cache overflow index, Indicates the average cache usage in the sub-period. Indicates the frequency of buffer overflow events in the sub-period, Indicates the extent to which the cache usage rate deviates from the normal range, indicating the degree of fluctuation in cache usage. T Indicates the total duration of the sub-period. , , They represent the average cache usage, the frequency of cache overflow events, and the weight of the cache usage deviation from the normal range.

9. The intelligent operation and maintenance management system for electric furnace equipment based on gateway data collection according to claim 3 is characterized in that: In each sub-period, after abnormal analysis of the proportion of data packets lost during data transmission, the steps to generate the data packet loss rate floating index are as follows: In each sub-period, get the total number of packets expected to be transmitted , the actual number of packets lost And the baseline loss rate ,The baseline loss rate is the packet loss rate under an ideal ,situation, which is used to evaluate the change of the actual loss rate; Calculate the actual loss rate, the calculation expression is: , Indicates the actual loss rate; Calculate the loss rate change value. The loss rate change value is defined as the change in the actual loss rate relative to the baseline loss rate. The calculation expression is: , where Indicates the change value of loss rate; Smooth the change in loss rate. The smoothing expression is: , where Indicates the smoothed loss rate change value of the current period Indicates the change value of the smoothed loss rate in the previous period, It represents the change value of loss rate after smoothing. represents the smoothing factor, ; Calculate the floating index of packet loss rate. The calculation expression is: , where Indicates the floating index of packet loss rate. Indicates the base value for normalization calculations.

Images