GIS equipment status monitoring method and system based on mobile Internet of Things

Abstract

The present invention discloses a GIS equipment status monitoring method and system based on mobile Internet of Things, which relates to the field of monitoring and control technology of power systems, including building a wireless network platform to obtain sensor signal data; performing signal conditioning of sensor data according to the signal characteristics of different types of sensors; extracting and classifying multi-type characteristic signals from the signal-conditioned data through multi-technical fusion; and performing phased real-time partial discharge monitoring of GIS equipment through multi-method joint detection to obtain target monitoring results. The present invention takes advantage of the joint operation of multiple sensors, eliminates the limitations of a single or a small number of sensors, improves the effectiveness and accuracy of partial discharge detection in diagnosing the insulation status of GIS equipment, enhances the anti-interference ability of the detection system and the detection sensitivity and efficiency of the system, improves the critical online monitoring function, and accumulates experience for early detection of internal discharge hazards in GIS and improving the accuracy of fault detection.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring and controlling power systems, and in particular to a GIS equipment status monitoring method and system based on mobile Internet of Things. Background Art

[0002] Gas Insulated Switchgear (GIS) with SF6 as the insulating medium is also called enclosed combined electrical appliances. Compared with conventional electrical appliances, GIS has the advantages of small footprint, compact structure, good electromagnetic compatibility, safe and reliable operation, etc. GIS is increasingly widely used in power systems. At present, the advanced diagnosis of internal discharge faults in 110 kV GIS equipment is still in the exploratory stage.

[0003] Insulation defects in GIS operation have seriously threatened the safe operation of the power system. Latent foreign matter may cause partial discharges of varying degrees in GIS due to manufacturing or long-term operation. Long-term discharges can cause insulation degradation of equipment. If not discovered and handled in time, it may even cause breakdown or flashover, resulting in serious consequences.

[0004] The research on critical monitoring technology of GIS equipment is of great significance for timely grasping the internal defect status of equipment, realizing equipment status evaluation and risk assessment, and realizing status maintenance of GIS equipment. Acquiring accurate GIS internal status information through critical monitoring is the premise of realizing status maintenance. Power outage detection, live detection and online monitoring are all basic means to obtain status information of substation equipment. These three detection methods have their own emphasis and advantages, as well as their own limitations and shortcomings. The present invention will break the current application difference between power outage detection instruments and live detection instruments, expand the functions of live detection instruments, and enable them to have online monitoring capabilities. It mainly has the following advantages: 1) Improve detection efficiency. Compared with existing independent detection instruments, this system has online monitoring capabilities. For detection objects with fault hidden danger characteristics or unclear status or requiring longitudinal comparison to verify the status, it can be switched to online mode at any time for continuous and tracking detection; compared with existing online monitoring devices, the application of this system does not require relevant installation and debugging, trenching and laying engineering cooperation measures, and can quickly enter the online monitoring state; for data reading and analysis, it can be carried out in fixed or even mobile places within the wide area coverage of mobile communications using various client terminals such as PC, mobile phone, PAD, etc. 2) Improve detection accuracy. Compared with the existing online monitoring mode, this system has instrument characteristics, strong detection pertinence, and can achieve higher and deeper detection accuracy. 3) Good economy. Compared with the installed online monitoring device, which costs millions of dollars, and most of the time the working operation is invalid detection. The monitoring effect can be fully achieved by the system developed in this project, but the economic investment must be at least one order of magnitude lower, and it can be used repeatedly in a mobile manner. 4) Reduce maintenance workload. Compared with the huge on-site maintenance workload of online monitoring devices, the maintenance of this system does not need to be limited to the site. It adopts a module replacement method. The calibration of the detection equipment is completely consistent with the current detection equipment and can be achieved by the current laboratory. Summary of the invention

[0005] In view of the above existing problems, the purpose of the present invention is to eliminate the influence of random pulse interference existing on site on the detection results, solve the problem that the defect type cannot be identified when multiple local discharge sources coexist, further promote the development of existing GIS local discharge detection technology and detection data processing and analysis methods, and improve the sensitivity of detection and the accuracy of defect type identification. The Internet of Things-based GIS critical monitoring technology of the present invention can be promoted and applied as an independent diagnostic means in GIS live detection work, and can also be fixed on GIS as a live monitoring means to realize online monitoring function, which is used for automatic pattern recognition of defect types. The present invention is of great significance to better grasp the internal insulation status of GIS equipment, ensure the safe and reliable operation of GIS equipment, further promote the development of GIS equipment status maintenance work, and improve the safety and stability of high-voltage system operation, and can generate huge economic efficiency and social benefits.

[0006] In order to solve the above technical problems, a GIS equipment status monitoring method based on mobile Internet of Things is proposed, including:

[0007] Build a wireless network platform to obtain sensor signal data; perform signal conditioning on sensor data according to the signal characteristics of different types of sensors; extract and classify multiple types of characteristic signals from the conditioned data through multi-technology fusion; and conduct phased real-time partial discharge monitoring of GIS equipment through multi-method joint detection to obtain target monitoring results.

[0008] As a preferred solution of the GIS equipment status monitoring method based on mobile Internet of Things described in the present invention, wherein: the sensor signal data includes building a wireless network platform to connect the detection front end, the client terminal and the server;

[0009] The detection front end, the client terminal, the server and the wireless network are connected using the first communication mode and the second communication mode;

[0010] The second communication mode is that the detection front end and the client terminal are connected by a local wireless network to form a power outage or power-on detection network architecture, and the front end detection unit is correspondingly designed with a local wireless network module;

[0011] The second communication mode is that the detection front end, the client terminal and the server use the wide area wireless network to form an online monitoring network architecture, and the front end detection unit is correspondingly designed with a wide area wireless network module;

[0012] Ultra-high frequency sensors and ultrasonic sensors are arranged on the surface of GIS equipment to collect bus voltage, current, air pressure, temperature and partial discharge signals of the two sensors respectively.

[0013] As a preferred solution of the GIS equipment status monitoring method based on mobile Internet of Things described in the present invention, the signal conditioning includes dynamically conditioning the UHF sensor through a variable gain amplifier according to the signal characteristics of different types of sensors to obtain conditioning data of the UHF sensor;

[0014] Performing signal conditioning on the ultrasonic sensor through a dynamic range compression model to obtain conditioning data of the ultrasonic sensor;

[0015] The conditioned data of the two sensors are converted into digital signals through ADC respectively, and then packaged and added to the data transmission module.

[0016] As a preferred solution of the GIS equipment status monitoring method based on mobile Internet of Things described in the present invention, the multi-technology fusion includes extracting and classifying multi-type feature signals of the input conditioned digital signal by using the multi-technology fusion of multi-signal source sensing technology, signal conditioning technology, digital acquisition technology and data analysis and processing technology;

[0017] Multi-type feature signal extraction is to extract time-frequency features from the input signal using wavelet transform, set the first frequency band interval, the second frequency band interval and the third frequency band interval, when the extracted time-frequency feature belongs to high frequency in the first frequency band interval, when the extracted time-frequency feature belongs to ultra-high frequency in the second frequency band interval, when the extracted time-frequency feature belongs to low frequency in the third frequency band interval, calculate the signal energy distribution and define the instantaneous energy ;

[0018] Based on the extracted characteristic signal, the instantaneous energy is optimized through the dynamic weight mechanism. :

[0019] ,

[0020] in, is the initial setting value, is the adjustment rate at time t, Represents the time average value of the feature, and classifies the optimized signal: when the optimized signal data is less than the first threshold, the current optimized signal data is judged as normal data; when the optimized signal data exceeds the first threshold and is less than the second threshold, the current optimized signal data is judged as potential fault data; when the optimized signal data exceeds the second threshold, the current optimized signal data is judged as fault data;

[0021] Determine the consistency and difference between high frequency, ultra-high frequency and optimized signal data.

[0022] As a preferred solution of the GIS equipment status monitoring method based on mobile Internet of Things described in the present invention, the multi-method joint detection includes, after judging the data is valid according to the consistency, performing stage real-time partial discharge monitoring on the equipment in online operation according to the difference combined with the multi-method joint detection method to judge the type of partial discharge defect existing:

[0023] ,

[0024] in, represents the final classified defect type, d is the index of different defect types, is the feature vector of classification d, is a small perturbation coefficient to prevent the model from overfitting; It is the overall difference result index of the difference result combined with the multi-method joint detection method;

[0025] Obtain target monitoring results, adopt a distributed structure design, store the test results in the background database, perform GIS critical care monitoring analysis based on the target monitoring results, and adjust the equipment through the detection unit during the monitoring process.

[0026] As a preferred solution of the GIS equipment status monitoring method based on mobile Internet of Things described in the present invention, wherein: the GIS critical disease monitoring and analysis includes locating the partial discharge defect signal that occurs according to the target monitoring result;

[0027] According to the synchronously recorded sensor signal data, the changing trends and rules are analyzed, and the influence of sensor signal data on partial discharge defect signals is studied:

[0028] ,

[0029] in, represents the change of the monitoring signal at time t, is the signal of the previous moment, The monitoring signal value at the previous moment, Indicates the influence weight of the total difference result I on the change amount, Representation function The weight of the impact on the change, It is a complex function that depends on the defect location, and Y represents the spatial position of the defect.

[0030] As a preferred solution of the GIS equipment status monitoring method based on mobile Internet of Things described in the present invention, the equipment adjustment includes adopting an intermittent working mode, adjusting the working sleep time, and waking up in a variety of ways;

[0031] The detection unit ensures that its internal operating temperature is within the appropriate range. In high outdoor temperatures, it activates the heat dissipation function to prevent overheating.

[0032] In case of low outdoor temperature, an auxiliary heating system is installed to ensure the normal operation of the unit.

[0033] Another object of the present invention is to provide a GIS equipment status monitoring system based on mobile Internet of Things. The present invention solves technical problems in GIS equipment status monitoring, including realizing real-time remote monitoring of equipment, improving the accuracy and timeliness of signal data transmission, accurately monitoring and intelligently diagnosing equipment status through advanced data processing and analysis technology, identifying and locating equipment defects, and automatically adjusting equipment to optimize maintenance processes, thereby improving the efficiency and safety of equipment maintenance, reducing downtime, and reducing maintenance costs.

[0034] As a preferred solution of the GIS equipment status monitoring system based on mobile Internet of Things described in the present invention, it is characterized by comprising a wireless network platform, a communication module, and a monitoring and analysis module;

[0035] The wireless network platform establishes a wireless network connection, ensures smooth communication between the detection front end, the client terminal and the server, receives sensor signal data from the detection front end, provides stable network services, and supports data transmission in the first communication mode and the second communication mode;

[0036] The communication module includes a first communication module and a second communication module, which detects the front-end acquisition of sensor signal data, performs signal conditioning and ADC conversion on the acquired sensor signal data, and sends the data to the back-end server through the data transmission module;

[0037] The monitoring and analysis module receives conditioned signal data, uses multi-signal source sensing technology to perform data fusion, applies signal conditioning technology, digital acquisition technology and data analysis and processing technology to extract multiple types of characteristic signals, obtains optimized data, classifies the optimized data, determines the data status, performs consistency and difference analysis on high-frequency, ultra-high-frequency and low-frequency signal data, and based on the analysis results, uses a multi-method joint detection method to perform stage-by-stage real-time partial discharge monitoring of the equipment, determines the type of partial discharge defects, and based on the monitoring results, performs equipment adjustments through the detection unit to ensure the normal operation of the equipment.

[0038] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the GIS equipment status monitoring method based on mobile Internet of Things are implemented.

[0039] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the GIS equipment status monitoring method based on mobile Internet of Things are implemented.

[0040] Beneficial effects of the present invention: The present invention focuses on using GIS ultrasonic and ultra-high frequency method data fusion technology, based on the Internet of Things technology and wireless communication technology, to reasonably control and use the information of each sensor, so that its redundant or complementary information in time and space is combined according to standards such as IEC61850, so as to obtain a one-time interpretation or description of the object being tested. The application of multi-sensor fusion technology in partial discharge detection can give play to the advantages of multi-sensor joint operation, eliminate the limitations of a single or a small number of sensors, and greatly improve the effectiveness and accuracy of partial discharge detection for GIS equipment insulation condition diagnosis. At the same time, the discharge information of multiple sensors is integrated, so that the advantages of each sensor are complementary, the anti-interference ability of the detection system is enhanced, and the detection sensitivity and detection efficiency of the system are improved, and the critical online monitoring function is improved. The GIS multi-channel critical monitoring technology is studied, and the wireless networking technology is used to detect the suspected abnormal gas chamber partial discharge signal in real time and continuously, taking into account the voltage, current, air pressure and temperature change trends in the same period, automatically warning the characteristic spectrum, and dynamically recording the complete partial discharge process of the gas chamber. In order to discover the hidden dangers of internal discharge in GIS in advance, accumulate experience to further improve the accuracy of fault detection, and ensure the safe and stable operation of GIS substations. In addition, it has the function of locating gas chamber faults during GIS on-site AC withstand voltage test after fault repair. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0042] Figure 1 An overall flow chart of a GIS equipment status monitoring method based on mobile Internet of Things provided for one embodiment of the present invention.

[0043] Figure 2 A system solution flow chart of a GIS equipment status monitoring system based on mobile Internet of Things provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0047] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0048] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0049] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides a GIS equipment status monitoring method based on mobile Internet of Things, comprising:

[0051] S1: Build a wireless network platform to obtain sensor signal data.

[0052] Furthermore, the construction of the wireless network platform includes connecting a detection front end, a client terminal and a server.

[0053] The detection front end, client terminal, server and wireless network access adopt the first communication mode and the second communication mode:

[0054] The second communication mode is that the detection front end and the client terminal are connected by a local wireless network to form a power outage or power-on detection network architecture, and the front end detection unit is correspondingly designed with a first communication module, namely, a local wireless network module;

[0055] The second communication mode is that the detection front end, client terminal and server use the wide area wireless network to form an online monitoring network architecture, and the front end detection unit is correspondingly designed with a second communication module, namely, a wide area wireless network module.

[0056] The server can use China Unicom WCDMA's wide area wireless network to connect to the front-end detection unit and the client terminal. You can choose 3G or 4G network, PC, mobile phone, PAD as the client terminal.

[0057] For the wireless LAN of the communication unit, industrial WIFI modules are considered, with a frequency range of 2.4 to 2.4835 GHz, a transmission rate of gigabit, and a transmission distance of up to 100 meters indoors and 500 meters outdoors; for the wireless WAN, 3G and 4G are considered.

[0058] Ultra-high frequency sensors and ultrasonic sensors are arranged on the surface of GIS equipment to collect bus voltage, current, air pressure, temperature and partial discharge signals of the two sensors respectively.

[0059] In addition, the frequencies of various device status information are different. The frequency of signals mainly used to detect voltage and current is generally low, while the frequency of partial discharge signals is generally in the megahertz range, requiring the collection of signals in various frequency bands. When designing AD, compatibility with multiple detection frequency bands must be considered to adapt to the collection of various frequency signals.

[0060] In order to make the front-end detection more maneuverable and portable, the product design must develop in the direction of miniaturization. When designing the functional circuit, programmable logic devices (FPGA), ASIC circuits, and DSP signal processing chips are used. The BGA packaged chips can increase the integration by two to three times without changing the volume, and at the same time have a smaller volume, better heat dissipation and electrical performance. Miniaturization requires that the product design should be anti-integrated instrument large and comprehensive design ideas, modular design of functional components, and flexible construction of the detection system according to the on-site test requirements, so that the object form is dispersed and the function is centralized and comprehensive.

[0061] S2: According to the signal characteristics of different types of sensors, signal conditioning of sensor data is performed separately.

[0062] Furthermore, according to the signal characteristics of different types of sensors, corresponding signal conditioning and acquisition circuits are designed respectively; the UHF sensor is dynamically conditioned through a variable gain amplifier to obtain the conditioning data of the UHF sensor. :

[0063] ,

[0064] ,

[0065] in, is the original signal input of the UHF sensor, is the signal output of the UHF sensor, is the UHF signal gain adjusted by the variable gain amplifier, is the proportionality constant of the gain, is the signal amplitude coefficient, Indicates the raw signal strength of the incoming UHF sensor, is the gain offset constant.

[0066] The ultrasonic sensor performs signal conditioning through a dynamic range compression model to obtain conditioning data of the ultrasonic sensor. :

[0067] ,

[0068] ,

[0069] in, and are the original signal output and original signal input of the ultrasonic sensor respectively, is the threshold value, represents the dynamic adjustment factor of the ultrasonic signal, is the compression factor, is an adjustable coefficient that affects the compression sensitivity, is the adaptive threshold in different environments, Indicates the original signal strength of the ultrasonic sensor after signal processing.

[0070] The conditioned data of the two sensors are converted into digital signals through ADC respectively, and then packaged and added to the data transmission module.

[0071] S3: Through multi-technology fusion, the signal conditioned data is used to extract and classify multiple types of feature signals.

[0072] Furthermore, the multi-technology integration of multi-signal source sensing technology, signal conditioning technology, digital acquisition technology and data analysis and processing technology is used to extract and classify multi-type feature signals of the input conditioned digital signal;

[0073] Multi-type feature signal extraction is to extract time-frequency features from the input signal using wavelet transform, set the first frequency band interval, the second frequency band interval and the third frequency band interval, when the extracted time-frequency feature belongs to high frequency in the first frequency band interval, when the extracted time-frequency feature belongs to ultra-high frequency in the second frequency band interval, when the extracted time-frequency feature belongs to low frequency in the third frequency band interval, calculate the signal energy distribution And define the instantaneous energy :

[0074] ,

[0075] in, represents the energy distribution of the signal at frequency f, T is the total duration of the observation time window, The signal value at time t, Indicates the frequency band of the corresponding interval, is an improved windowing function;

[0076] Based on the extracted characteristic signal, the instantaneous energy is optimized through the dynamic weight mechanism. ,in, is the initial setting value, is the adjustment rate at time t, Represents the time average value of the feature. It is set that when the optimized signal data is less than the first threshold, the current optimized signal data is judged to be normal data. When the optimized signal data exceeds the first threshold and is less than the second threshold, the current optimized signal data is judged to be potential fault data. When the optimized signal data exceeds the second threshold, the current optimized signal data is judged to be fault data.

[0077] Determine the consistency and difference between high frequency, ultra-high frequency and optimized signals. The consistency is:

[0078] ,

[0079] The differences are:

[0080] ,

[0081] The larger the value, the greater the difference.

[0082] in, is the consistency measure between a and b, where a and b are any two combinations of high frequency, ultra-high frequency, and optimized signals, respectively. is the covariance of a and b, indicating the linear relationship between the two variables; and are the variances of a and b, respectively, measuring the degree of data dispersion; is the difference measure between the dynamic probability distributions P and Q, is the probability distribution P at time t, The probability distribution Q at time t, is the adjustment factor used to influence the flexibility of difference detection; To provide real-time feedback on adjustment items, affecting the final difference evaluation.

[0083] S4: Through multi-method joint detection, the target monitoring results are obtained by performing phased real-time partial discharge monitoring of GIS equipment.

[0084] Furthermore, the existing general testing method is that the testers determine the location and number of test points after arriving at the site, which has a certain degree of randomness and is seriously affected by the experience and technical level of the testers. The consequences may be unreasonable point selection and missed tests. During the general test, each test point only lasts for a few seconds, and partial discharge itself has a certain degree of randomness, especially when the discharge is not intense, which leads to missed tests. The test results of the existing detection methods cannot be used for subsequent analysis, and it is impossible to carry out centralized data management, historical data accumulation, in-depth analysis, etc., which seriously restricts the development of partial discharge detection technology.

[0085] When the data is judged to be valid according to the consistency, the equipment in online operation is monitored for partial discharge in real time according to the difference combined with a multi-method joint detection method:

[0086] ,

[0087] in, The response time of the i-th signal, n is the number of detection methods, is the importance weight of the i-th detection method, , For adjustment and The intensity of the impact on outcome I, is the correction factor, represents additional factors that affect the defect results, Adjust the index of the influence of A in the result, i is the variable index.

[0088] Determine the type of partial discharge defect that exists:

[0089] ,

[0090] in, represents the final classified defect type, d is the index of different defect types, is the feature vector of classification d, is a small perturbation coefficient to prevent the model from overfitting.

[0091] Obtain target monitoring results, adopt distributed structure design, and store the detection results in the background database.

[0092] According to the target monitoring results, GIS critical monitoring and analysis are carried out to locate the partial discharge defect signals that occur. , further locate the defect signal:

[0093] ,

[0094] Where Y represents the spatial position of the defect, is the number of monitoring points, The first signal data of the mth monitoring point, The propagation speed of the data at the mth monitoring point, The signal time delay of the mth monitoring point is the time from the measurement point to the destination point; represents the noise level of the system environment, and C represents the interference degree of signal processing.

[0095] According to the synchronously recorded sensor signal data, the changing trends and rules are analyzed, and the influence of sensor signal data on partial discharge defect signals is studied:

[0096] ,

[0097] in, represents the change of the monitoring signal at time t, is the signal of the previous moment, The monitoring signal value at the previous moment, Indicates the influence weight of the total difference result I on the change amount, Representation function The weight of the impact on the change, It is a complex function that depends on the defect location, and Y represents the spatial position of the defect.

[0098] During this process, the present invention pays special attention to the consistency and diversity of signal data to ensure the accuracy of the monitoring results. As shown in Table 1, the performance of different technologies in terms of the quality of three types of data, fault detection accuracy and battery life are compared for the data of the present invention.

[0099] Table 1

[0100] ,

[0101] In terms of fault detection accuracy, the embodiment of the present invention reached 90%, and the optimized version reached 95%, which is much higher than the 70% and 75% of the prior art. This significantly improved accuracy directly reflects the innovation and practicality of the present invention in equipment status monitoring.

[0102] In addition, in terms of battery life, the embodiment and optimized version of the present invention reach 12 hours and 15 hours respectively, which is significantly improved compared with 8 hours and 10 hours in the prior art. This improvement not only reduces the maintenance frequency, but also enhances the reliability of the monitoring system.

[0103] In summary, the embodiments of the present invention demonstrate their innovation and advantages in terms of signal data processing, fault detection accuracy, and battery life, and provide a more efficient and accurate solution for GIS equipment status monitoring.

[0104] It should be noted that during the monitoring process, equipment adjustments are performed through the detection unit.

[0105] In order to solve the problem of long-term online monitoring of the front-end detection unit in battery-powered mode, the battery selection and its low-power design are mainly considered. Low-power processors and low-power peripheral chips are used as much as possible, and the pull-up or pull-down resistors of the signal are used with caution in the circuit. The settings are set to minimize unnecessary energy waste and reduce heat. The intermittent working mode is adopted, and the working sleep time can be adjusted according to the requirements, and multiple wake-up methods are supported.

[0106] The detection unit is used online outdoors and is required to meet IP65 protection level. Electromagnetic shielding and other measures are taken to prevent electromagnetic radiation from affecting the electronic components of the detection unit, reduce interference with measurement, and ensure reliable communication.

[0107] The detection unit ensures that its internal operating temperature is within the appropriate range. When the outdoor temperature is high in summer, the heat dissipation function is activated to prevent overheating; when used in colder areas in winter, an auxiliary heating system can be installed to ensure the normal operation of the unit. In order to achieve rapid and reliable fixation of the front-end detection unit and the substation equipment under test, belt binding, magnetic suction, air suction and other methods can be used according to the different materials and shapes of the shells of the substation equipment under test. Substation equipment with iron shells can be fixed by magnetic suction; substation equipment with non-iron shells can be fixed by belt binding; substation equipment with smoother shells can be fixed by air suction. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, ordinary technicians in this field should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be covered in the scope of the claims of the present invention.

[0108] Embodiment 2, the second embodiment of the present invention, is different from the first two embodiments in that:

[0109] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0111] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0112] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] Example 3, reference Figure 2 , which is the third embodiment of the present invention, and provides a GIS equipment status monitoring system based on mobile Internet of Things, including a wireless network platform 10, a communication module 20, and a monitoring and analysis module 30;

[0114] The wireless network platform 10 establishes a wireless network connection, ensures smooth communication between the detection front end, the client terminal and the server, receives sensor signal data from the detection front end, provides stable network services, and supports data transmission in the first communication mode and the second communication mode;

[0115] The communication module 20 includes a first communication module and a second communication module, which detects the front-end acquisition of sensor signal data, performs signal conditioning and ADC conversion on the acquired sensor signal data, and sends it to the back-end server through the data transmission module;

[0116] The monitoring and analysis module 30 receives the conditioned signal data, utilizes the multi-signal source sensing technology to perform data fusion, applies the signal conditioning technology, the digital acquisition technology and the data analysis and processing technology, extracts multiple types of characteristic signals, obtains the optimized data, classifies the optimized data, determines the data status, performs consistency and difference analysis on the high-frequency, ultra-high-frequency and low-frequency signal data, and according to the analysis results, adopts the multi-method joint detection method to perform stage-by-stage real-time partial discharge monitoring on the equipment, determines the type of partial discharge defect, and according to the monitoring results, performs equipment adjustment through the detection unit to ensure the normal operation of the equipment.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A GIS equipment status monitoring method based on mobile Internet of Things, characterized by: include, Build a wireless network platform to obtain sensor signal data; According to the signal characteristics of different types of sensors, signal conditioning of sensor data is performed respectively; Through multi-technology fusion, the signal-conditioned data is used to extract and classify multiple types of characteristic signals; Through multi-method joint detection, the target monitoring results are obtained by performing phased real-time partial discharge monitoring of GIS equipment; The sensor signal data includes building a wireless network platform to connect the detection front end, client terminal and server; The detection front end, the client terminal, the server and the wireless network are connected using the first communication mode and the second communication mode; The first communication mode is that the detection front end and the client terminal are connected by a local wireless network to form a power outage or power-on detection network architecture, and the front end detection unit is correspondingly designed with a local wireless network module; The second communication mode is that the detection front end, the client terminal and the server use the wide area wireless network to form an online monitoring network architecture, and the front end detection unit is correspondingly designed with a wide area wireless network module; Ultra-high frequency sensors and ultrasonic sensors are arranged on the surface of GIS equipment to collect bus voltage, current, air pressure, temperature and partial discharge signals of the two sensors respectively; The signal conditioning includes dynamically conditioning the UHF sensor through a variable gain amplifier according to the signal characteristics of different types of sensors to obtain conditioning data of the UHF sensor; Performing signal conditioning on the ultrasonic sensor through a dynamic range compression model to obtain conditioning data of the ultrasonic sensor; The conditioned data of the two sensors are converted into digital signals through ADC respectively, and then packaged and added to the data transmission module; The multi-technology fusion includes extracting and classifying multi-type characteristic signals of the input conditioned digital signal by utilizing the multi-technology fusion of multi-signal source sensing technology, signal conditioning technology, digital acquisition technology and data analysis and processing technology; The multi-type feature signal extraction is to extract time-frequency features from the input signal using wavelet transform, set the first frequency band interval, the second frequency band interval and the third frequency band interval, when the extracted time-frequency feature belongs to high frequency in the first frequency band interval, when the extracted time-frequency feature belongs to ultra-high frequency in the second frequency band interval, when the extracted time-frequency feature belongs to low frequency in the third frequency band interval, calculate the signal energy distribution and define the instantaneous energy E inst (t); Based on the extracted characteristic signal, the instantaneous energy is optimized by the dynamic weight mechanism to obtain the signal W dynamic : Among them, W base is the initial setting value, η t is the adjustment rate at time t, Represents the time average value of the feature, and classifies the optimized signal: when the optimized signal data is less than the first threshold, the current optimized signal data is judged as normal data; when the optimized signal data exceeds the first threshold and is less than the second threshold, the current optimized signal data is judged as potential fault data; when the optimized signal data exceeds the second threshold, the current optimized signal data is judged as fault data; Determine the consistency and difference between high frequency, ultra-high frequency and optimized signal data. The consistency is: The differences are: D dynamic The larger the value of (P||Q), the greater the difference; Among them, C(a,b) is the consistency measure between a and b, a and b are any two combinations of high frequency, ultra-high frequency, and optimized signals, Cov(a,b) is the covariance of a and b, indicating the linear relationship between the two variables; Var(a) and Var(b) are the variances of a and b, respectively, measuring the degree of data dispersion; D dynamic (P||Q) is the difference measure between the dynamic probability distributions P and Q, P(t) is the probability distribution P at time t, Q(t) is the probability distribution Q at time t, λ is the adjustment coefficient used to affect the flexibility of difference detection; δ(t) is the real-time feedback adjustment item that affects the final difference evaluation; The multi-method joint detection includes, after judging the data is valid according to the consistency, performing stage-by-stage real-time partial discharge monitoring on the equipment in online operation according to the difference combined with the multi-method joint detection method: Among them, t i The response time of the i-th signal, n is the number of detection methods, γ i is the importance weight of the i-th detection method, θ1 and θ2 are used to adjust E inst,i and t i The intensity of the impact on the result I, B is the correction coefficient, A represents the additional factor affecting the defect result, θ3 adjusts the impact of A in the result, and i is the variable index; Determine the type of partial discharge defect that exists: D=argmax d (I·(v d +∈)) Where D represents the final classified defect type, d represents the index of different defect types, and v represents the final classified defect type. d is the feature vector of classification d, ∈ is a small perturbation coefficient to prevent the model from overfitting; I is the total difference result index of the difference result combined with the multi-method joint detection method; Obtain target monitoring results, adopt a distributed structure design, store the test results in the background database, perform GIS critical care monitoring analysis based on the target monitoring results, and adjust the equipment through the detection unit during the monitoring process.

2. The GIS equipment status monitoring method based on mobile Internet of Things as claimed in claim 1, characterized in that: The GIS critical monitoring and analysis includes locating the partial discharge defect signal that occurs according to the target monitoring results; According to the synchronously recorded sensor signal data, the changing trends and rules are analyzed, and the influence of sensor signal data on partial discharge defect signals is studied: ΔN t =ω1N t-1 +ω2I+ω3F(Y)+η t Among them, ΔN t represents the change of the monitoring signal at time t, ω1 is the signal at the previous moment, N t-1 The monitoring signal value at the previous moment, ω2 represents the influence weight of the total difference result I on the change, ω3 represents the influence weight of the function F(Y) on the change, F(Y) is a complex function that depends on the defect position, and Y represents the spatial position of the defect.

3. The GIS equipment status monitoring method based on mobile Internet of Things as claimed in claim 2 is characterized in that: The device adjustment includes adopting an intermittent working mode, adjusting the working sleep time, and waking up in various ways; The detection unit ensures that its internal operating temperature is within the appropriate range. In high outdoor temperatures, it activates the heat dissipation function to prevent overheating. In case of low outdoor temperature, an auxiliary heating system is installed to ensure the normal operation of the unit.

4. A system using the GIS equipment status monitoring method based on mobile Internet of Things as claimed in any one of claims 1 to 3, characterized in that: Including wireless network platform, communication module, monitoring and analysis module; The wireless network platform establishes a wireless network connection, ensures smooth communication between the detection front end, the client terminal and the server, receives sensor signal data from the detection front end, provides stable network services, and supports data transmission in the first communication mode and the second communication mode; The communication module includes a first communication module and a second communication module, which detects the front-end acquisition of sensor signal data, performs signal conditioning and ADC conversion on the acquired sensor signal data, and sends the data to the back-end server through the data transmission module; The monitoring and analysis module receives conditioned signal data, uses multi-signal source sensing technology to perform data fusion, applies signal conditioning technology, digital acquisition technology and data analysis and processing technology to extract multiple types of characteristic signals, obtains optimized data, classifies the optimized data, determines the data status, performs consistency and difference analysis on high-frequency, ultra-high-frequency and low-frequency signal data, and based on the analysis results, uses a multi-method joint detection method to perform stage-by-stage real-time partial discharge monitoring of the equipment, determines the type of partial discharge defects, and based on the monitoring results, performs equipment adjustments through the detection unit to ensure the normal operation of the equipment.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the GIS equipment status monitoring method based on mobile Internet of Things described in any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the GIS equipment status monitoring method based on mobile Internet of Things described in any one of claims 1 to 3 are implemented.

Images