Switch cabinet digital twin data analysis method, device and equipment and storage medium

Abstract

The invention discloses a switch cabinet digital twinborn data analysis method, device and equipment and a storage medium, and belongs to the technical field of electrical design, and the method comprises the steps: obtaining the operation state data of a switch cabinet, and building a switch cabinet digital twinborn model; obtaining predicted state data of the switch cabinet according to the digital twin model of the switch cabinet; within a preset sampling time, obtaining a prediction difference value between the prediction state data and the operation state data, and constructing an associated parameter of each component in the switch cabinet based on the prediction difference value; and setting a weight coefficient of each component in the switch cabinet, establishing a switch cabinet operation state evaluation model based on the associated parameters and the weight coefficients, inputting the predicted state data into the state evaluation model, and evaluating the operation state of the switch cabinet. According to the invention, the digital twin model is constructed according to the real-time sampling data of the switch cabinet, the prediction data is obtained, the state of the switch cabinet is evaluated according to the sampling data and the prediction data, the prediction accuracy of the operation state of the switch cabinet is improved, and the electrical safety performance is improved.

Description

Technical Field

[0001] The present invention relates to the field of electrical design technology, and in particular to a switch cabinet digital twin data analysis method, device, equipment and storage medium. Background Art

[0002] The existing SCADA system only realizes basic data collection and fails to establish a dynamic data-driven model update mechanism. The data in each stage of design, manufacturing, and operation and maintenance are isolated. It only relies on traditional sensor sampling data (such as temperature and current). The prediction model is not accurate enough, resulting in the inability of prediction results to guide operation and maintenance decisions in real time.

[0003] Currently, switchgear cannot accurately predict equipment behavior under extreme working conditions during the design phase, and it is difficult to promptly identify progressive faults such as insulation degradation during the operation and maintenance phase. Faced with the higher requirements of new power systems for equipment intelligence, the existing technology system has shown obvious inadaptability. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to solve the problem that the current switch cabinet cannot accurately predict the equipment behavior under extreme working conditions during the design phase, and it is difficult to timely identify progressive faults such as insulation degradation during the operation and maintenance phase.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a switch cabinet digital twin data analysis method, which includes the following steps of obtaining the operating status data of the switch cabinet, the operating status data including electrical data information and environmental data information collected by sensors inside the switch cabinet; filtering and integrating the electrical data information and environmental data information to generate the operating status data of the switch cabinet, and establishing a digital twin model of the switch cabinet based on the operating status data; obtaining the predicted status data of the switch cabinet according to the switch cabinet digital twin model; within a preset sampling time, obtaining the predicted difference between the predicted status data and the operating status data, and constructing the associated parameters of each component in the switch cabinet based on the predicted difference; setting the weight coefficient of each component in the switch cabinet, establishing a switch cabinet operating status evaluation model based on the associated parameters and the weight coefficient, and inputting the predicted status data into the status evaluation model to evaluate the operating status of the switch cabinet.

[0007] As a preferred solution of the switch cabinet digital twin data analysis method described in the present invention, the obtaining of the operating status data of the switch cabinet includes collecting electrical data information and environmental data information through multiple sensors arranged at key positions of the switch cabinet, and uniformly encoding them after time alignment to generate operating status data with a timestamp.

[0008] As a preferred solution of the switch cabinet digital twin data analysis method described in the present invention, the construction of the associated parameters of each component in the switch cabinet includes performing statistical analysis of the mean value and standard deviation of the predicted state data and the operating state data within a preset sampling time to determine whether the set deviation range conditions are met. If the conditions are met, the associated parameters for describing the operating state offset of each component are constructed based on the mean value difference.

[0009] As a preferred solution of the switch cabinet digital twin data analysis method described in the present invention, the evaluation of the operating status of the switch cabinet includes setting weight coefficients for each component in the switch cabinet, constructing an operating status evaluation model based on the associated parameters and corresponding weights of each component, inputting the predicted status data into the status evaluation model, and outputting the operating status level of the switch cabinet.

[0010] As a preferred solution of the switch cabinet digital twin data analysis method described in the present invention, wherein: the obtaining of the predicted difference between the predicted state data and the operating state data, and constructing the associated parameters of each component in the switch cabinet based on the predicted difference, includes: obtaining the predicted difference between the predicted state data and the operating state data within a preset sampling time; calculating the adjustment mapping relationship of each component in the switch cabinet according to the predicted difference; obtaining the associated parameters of each component in the switch cabinet according to the adjusted mapping relationship; the obtaining of the predicted difference between the predicted state data and the operating state data within the preset sampling time includes: obtaining the first average value and the first standard deviation of the predicted state data within the preset sampling time, and obtaining the second average value and the second standard deviation of the operating state data within the preset sampling time; judging whether the first standard deviation and the second standard deviation are within the preset deviation range; if they are within the preset deviation range, calculating the difference between the first average value and the second average value as the predicted difference; the calculating of the adjusted mapping relationship of each component in the switch cabinet according to the predicted difference includes: using the predicted difference to superimpose the predicted state data to generate adjustment data; obtaining the adjustment mapping relationship of each component in the switch cabinet through incremental learning based on the adjustment data within the preset sampling time.

[0011] As a preferred solution of the switch cabinet digital twin data analysis method described in the present invention, wherein: the predicted state data is input into the state evaluation model to evaluate the operating state of the switch cabinet, including setting the weight coefficient of each component in the switch cabinet; establishing a switch cabinet operating state evaluation model based on the relationship between the associated parameters and the switch cabinet state, and combining the weight coefficient; inputting the predicted state data of the switch cabinet into the switch cabinet operating state evaluation model to evaluate the operating state of the switch cabinet.

[0012] As a preferred solution of the switch cabinet digital twin data analysis method described in the present invention, wherein: the predicted state data is input into the state evaluation model to evaluate the operating state of the switch cabinet, and also includes constructing a historical query library according to the corresponding operating state obtained by inputting different predicted state data into the switch cabinet operating state evaluation model; when obtaining the operating state data of the switch cabinet, it is determined whether it is included in the historical query library; if it is included in the historical query library, the state of the switch cabinet is determined to be the corresponding operating state in the historical query library.

[0013] Another object of the present invention is to provide a switch cabinet digital twin data analysis device.

[0014] To solve the above technical problems, the present invention provides the following technical solutions: a switch cabinet digital twin data analysis device, comprising: a data acquisition module, a model construction module, a data prediction module, a data calibration module and a status evaluation module; the data acquisition module is used to obtain the operating status data of the switch cabinet, and the operating status data includes electrical data information and environmental data information collected by sensors inside the switch cabinet; the model construction module is used to filter and integrate the electrical data information and the environmental data information to generate the operating status data of the switch cabinet, and establish a digital twin model of the switch cabinet based on the operating status data; the data prediction module is used to obtain the predicted status data of the switch cabinet according to the switch cabinet digital twin model; the data calibration module is used to obtain the predicted difference between the predicted status data and the operating status data within a preset sampling time, and construct the associated parameters of each component in the switch cabinet based on the predicted difference; the status evaluation module is used to set the weight coefficient of each component in the switch cabinet, establish a switch cabinet operating status evaluation model based on the associated parameters and the weight coefficient, and input the predicted status data into the status evaluation model to evaluate the operating status of the switch cabinet.

[0015] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of the switch cabinet digital twin data analysis method.

[0016] The present invention provides 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 switch cabinet digital twin data analysis method are implemented.

[0017] The beneficial effects of the present invention are as follows: the present invention can construct a digital twin model based on the real-time sampling data of the switch cabinet and obtain predicted data. At the same time, the switch cabinet status is evaluated based on the sampling data and predicted data, thereby improving the accuracy of the switch cabinet operating status prediction and improving the electrical safety performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 An overall flow chart of a switchgear digital twin data analysis method provided for one embodiment of the present invention.

[0020] Figure 2 A simulation diagram of the operating status of a switch cabinet according to a switch cabinet digital twin data analysis method provided by one embodiment of the present invention.

[0021] Figure 3 A schematic diagram of a digital twin model of a switch cabinet according to a switch cabinet digital twin data analysis method provided in one embodiment of the present invention.

[0022] Figure 4 A module diagram of a device solution for a switch cabinet digital twin data analysis device provided in accordance with one embodiment of the present invention. DETAILED DESCRIPTION

[0023] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0024] Example 1, with reference to Figures 1 to 3 , which is the first embodiment of the present invention, provides a switch cabinet digital twin data analysis method, including: obtaining the operating status data of the switch cabinet, the operating status data including electrical data information and environmental data information collected by sensors inside the switch cabinet; filtering and integrating the electrical data information and the environmental data information to generate the operating status data of the switch cabinet, and establishing a digital twin model of the switch cabinet based on the operating status data; obtaining the predicted status data of the switch cabinet according to the switch cabinet digital twin model; within a preset sampling time, obtaining the predicted difference between the predicted status data and the operating status data, and constructing the associated parameters of each component in the switch cabinet based on the predicted difference; setting the weight coefficient of each component in the switch cabinet, establishing a switch cabinet operating status evaluation model based on the associated parameters and the weight coefficient, and inputting the predicted status data into the status evaluation model to evaluate the operating status of the switch cabinet.

[0025] Existing SCADA systems only collect basic data and fail to establish a dynamic data-driven model update mechanism. Data from the design, manufacturing, and operation and maintenance phases are isolated, and the prediction models rely solely on traditional sensor data (such as temperature and current). Consequently, the inaccurate predictions make it impossible to guide real-time operation and maintenance decisions. Switchgear design cannot accurately predict equipment behavior under extreme operating conditions, and the operation and maintenance phase struggles to promptly identify progressive faults such as insulation degradation. Faced with the higher demands placed on intelligent equipment by the new power system, the existing technology system is clearly unsuitable.

[0026] The present invention provides a solution that can build a digital twin model based on the real-time sampling data of the switch cabinet and obtain predicted data. At the same time, the switch cabinet status is evaluated based on the sampling data and predicted data, thereby improving the accuracy of the switch cabinet operating status prediction and improving electrical safety performance.

[0027] S1. Obtaining the operating status data of the switch cabinet. The operating status data includes electrical data information and environmental data information collected by sensors inside the switch cabinet.

[0028] It should be noted that operating status data can be a structured data set that can reflect the current operating status of the switchgear after real-time collection and processing by sensors. It contains multi-dimensional information such as electrical characteristics, mechanical status, and environmental parameters, which is used to drive the digital twin model and support subsequent prediction and evaluation. For example, it can include electrical data (RMS current, RMS voltage, active power), thermal data (contact temperature, busbar temperature rise, cable joint hot spot temperature), mechanical data (circuit breaker opening and closing times, operating mechanism travel time), and environmental data (humidity, air pressure, SF6 gas concentration in the cabinet).

[0029] It should be understood that operating status data can be collected using sensors placed inside the switchgear. Sensors can be placed in key locations of the switchgear, such as circuit breaker contacts and busbars. For example, a Rogowski coil can be used to collect the switchgear main circuit current, and digital temperature sensors can be placed at key heat points such as circuit breaker contacts and busbar connections.

[0030] Step S1 includes:

[0031] S1.1. Collect electrical data and environmental data from sensors inside the switch cabinet.

[0032] S1.2. Filter and integrate the electrical data information and the environmental data information to generate the operating status data of the switch cabinet.

[0033] S1.3. Establish a digital twin model of the switchgear based on operating status data.

[0034] It should be noted that high-frequency noise can be eliminated and the characteristics of partial discharge signals can be retained by using wavelet transform (such as db4 wavelet basis). Based on the Precision Time Protocol (PTP), data acquisition within the error range of multi-sensor data timestamps can be achieved.

[0035] S2. Filter and integrate the electrical data information and environmental data information to generate the operating status data of the switchgear, and establish a digital twin model of the switchgear based on the operating status data.

[0036] The digital twin model of the switchgear can be a virtual model that is mapped to the physical switchgear in real time. It can include geometric structure, material properties, operating logic, and has self-calibration capabilities. A multi-physics field coupling model is built based on MATLAB / Simulink, and the input operating status data drives the model to achieve dynamic updates. The coupling model includes: Electrical sub-model: simulates the arc discharge characteristics during the opening and closing process of the circuit breaker. Thermal field sub-model: calculates the relationship between contact resistance and temperature rise based on the finite element method (FEM). Among them, the electrical sub-model can include the Cassie arc model, which is based on the steady-state characteristics of the arc and relates the arc voltage to the current density and arc temperature. It is suitable for the simulation of high current and short time arcs. Its differential equation form is:

[0037]

[0038] Where g is the arc conductance, Uarc is the arc voltage, E is the electric field intensity, and τ is the time constant.

[0039] Furthermore, the thermal field sub-model can establish a heat conduction model of the contacts and busbars based on Fourier's law and energy conservation equation:

[0040]

[0041] Where ρ is the material density, c p is the specific heat capacity, k is the thermal conductivity, Q is the Joule heat source, and T is the temperature.

[0042] S3. Obtain the predicted status data of the switch cabinet based on the switch cabinet digital twin model.

[0043] It should be noted that predicted status data can be the estimated results of future switchgear operating parameters calculated using the digital twin model. This includes multi-dimensional predictions such as electrical, thermal, and mechanical. By integrating physical model calculations with data-driven algorithms, early warning of potential equipment failures is achieved, providing the basis for subsequent correlation parameter construction and status assessment.

[0044] It should be understood that the Cassie model can be used to predict arc stability based on the collected electrical and thermal parameters of the switchgear, as well as environmental data. Based on the current current and voltage, the arc voltage, current waveform, and duration during circuit breaker operation are simulated, outputting dynamic changes in arc energy and conductivity for evaluating contact wear and arc extinguishing capability. Joule heating is calculated based on the input current density distribution, and the temperature field is solved and fed back to the electrical model. The material resistivity is updated to form a closed loop. Combined with contact surface roughness and contact pressure, the evolution of contact resistance with temperature and aging is predicted to provide an estimate of the switchgear's future operating parameters.

[0045] In one possible implementation, the preset sampling period is set to one hour. The first average value of the predicted state data (model output) is the mean of the predicted temperature over the one-hour period, and the first standard deviation is the fluctuation range of the predicted temperature. The same applies to the second average value and second standard deviation of the operating state data (measured values). If the standard deviation exceeds 10% (the preset deviation range), adaptive adjustment of the model parameters is triggered.

[0046] S4. Within a preset sampling time, obtain the predicted difference between the predicted state data and the operating state data, and construct the associated parameters of each component in the switch cabinet based on the predicted difference.

[0047] It should be noted that the prediction difference can be the quantitative difference between the predicted state data calculated by the digital twin model and the actual collected operating state data, and the degree of deviation between the model prediction and the actual operation is reflected through statistical analysis (such as mean difference, standard deviation ratio). The associated parameters can be constructed by analyzing the predicted difference between the predicted state data and the operating state data to form quantitative indicators reflecting the health status and performance changes of each component of the switchgear (such as contact resistance correction coefficient, busbar thermal expansion compensation value). It converts data differences into characteristic parameters that can be directly used for state assessment through mathematical models or algorithm mapping, and is the core basis for achieving fault warning and life prediction. The prediction difference can be mapped to component health parameters by adopting machine learning algorithms, such as Gradient Boosting Decision Tree (GBDT).

[0048] Step S4 includes:

[0049] S4.1. Obtain the predicted difference between the predicted state data and the operating state data within the preset sampling time.

[0050] S4.2. Calculate the adjustment mapping relationship of each component in the switch cabinet based on the predicted difference.

[0051] S4.3. Obtain associated parameters of each component in the switch cabinet according to the adjusted mapping relationship.

[0052] Step S4.1 includes:

[0053] S4.1.1. Obtain a first average value and a first standard deviation of the predicted state data within a preset sampling time, and obtain a second average value and a second standard deviation of the operating state data within the preset sampling time.

[0054] S4.1.2. Determine whether the first standard deviation and the second standard deviation are within the preset deviation range.

[0055] S4.1.3. If yes, calculate the difference between the first average value and the second average value as the predicted difference.

[0056] It should be noted that the predicted difference can be used to superimpose the predicted state data to generate adjustment data; and the adjustment mapping relationship of each component in the switch cabinet can be obtained through incremental learning based on the adjustment data within the preset sampling time.

[0057] Reference Figure 2 and Figure 3 , Figure 2 The middle is the operating status of each device in the switch cabinet, green represents normal, yellow represents minor fault, and red represents serious fault. Figure 3 The digital twin model in the system can be used for status monitoring and simulation can be performed by modifying parameters.

[0058] S5. Set weight coefficients for various components in the switchgear, establish a switchgear operating status evaluation model based on the associated parameters and the weight coefficients, input the predicted status data into the status evaluation model, and evaluate the operating status of the switchgear.

[0059] It should be noted that the Analytic Hierarchy Process (AHP) can be used to construct a judgment matrix through expert scoring, calculate the weight of each component (for example: circuit breaker: 0.5, bus: 0.3, sensor: 0.2), and then calculate the health index (0-100 points) or status level (normal / warning / fault) of the corresponding component based on the associated parameters.

[0060] For example, you can construct a formula to calculate: Where wi is the weight and f(xi) is the correlation parameter. A calculated health index greater than 85 indicates that the switchgear is operating normally. If the health index is between 60 and 85, the switchgear may be experiencing a minor fault, such as aging, and a warning is required. If the health index is less than 60, the switchgear is operating in a fault state, triggering an alarm.

[0061] Furthermore, when a partial discharge signal is detected, incremental learning is triggered. The current prediction difference and the partial discharge intensity (unit: pC) are added to the training set as new samples. An online learning algorithm is used to update and adjust the mapping relationship model to improve the ability to identify insulation aging. A historical query library can also be constructed by storing typical status data from the past three years. When the similarity between real-time data and a set of data in the historical library is greater than 90% (calculated based on cosine similarity), the historical evaluation conclusion is directly output.

[0062] Step S5 includes:

[0063] S5.1. Set the weight coefficients of each component in the switchgear.

[0064] S5.2. Based on the relationship between the associated parameters and the switchgear status, and combined with the weight coefficient, a switchgear operation status evaluation model is established.

[0065] S5.3. Input the predicted state data of the switchgear into the switchgear operation state evaluation model to evaluate the operation state of the switchgear.

[0066] Specifically, a historical query library can be constructed based on the corresponding operating status obtained by inputting different prediction status data into the switch cabinet operating status evaluation model; when obtaining the operating status data of the switch cabinet, it is determined whether it is included in the historical query library; if so, the status of the switch cabinet is determined to be the corresponding operating status in the historical query library.

[0067] It should be understood that the judgment matrix is ​​constructed through expert scoring, and the component weight coefficients (such as circuit breaker, busbar, and sensor weights) are set. The Analytic Hierarchy Process (AHP) can be used to construct the judgment matrix through expert scoring, calculate the weight of each component (for example: circuit breaker: 0.5, busbar: 0.3, sensor: 0.2), and then calculate the health index (0-100 points) or status level (normal / warning / fault) of the corresponding component based on the associated parameters. For example, the formula can be constructed for calculation: Where wi is the weight and f(xi) is the correlation parameter. A calculated health index greater than 85 indicates that the switchgear is operating normally. If the health index is between 60 and 85, the switchgear may be experiencing a minor fault, such as aging, and a warning is required. If the health index is less than 60, the switchgear is operating in a fault state, triggering an alarm.

[0068] In this embodiment, by setting the weight coefficients of each component in the switch cabinet; according to the relationship between the associated parameters and the switch cabinet status, combined with the weight coefficients, a switch cabinet operation status evaluation model is established; the predicted status data of the switch cabinet is input into the switch cabinet operation status evaluation model to evaluate the operation status of the switch cabinet. According to the corresponding operation status obtained by inputting different predicted status data into the switch cabinet operation status evaluation model, a historical query library is constructed; when obtaining the operation status data of the switch cabinet, it is determined whether it is included in the historical query library; if so, the status of the switch cabinet is determined to be the corresponding operation status in the historical query library. By setting the component weight coefficients, a systematic analysis of the health status of the switch cabinet is achieved to avoid misjudgment of a single parameter. The weight can be automatically adjusted according to historical fault data to adapt to equipment aging and changes in the operating environment. Accumulate historical fault data to improve the generalization ability of the model and avoid repeated misjudgment of similar faults.

[0069] In this embodiment, a switchgear digital twin model is established by acquiring the switchgear's operating status data; predicted status data for the switchgear is obtained based on the switchgear digital twin model; associated parameters for each switchgear component are constructed based on the predicted difference between the predicted status data and the operating status data; and the switchgear's operating status is evaluated based on the associated parameters. This allows the digital twin model to be constructed based on the switchgear's real-time sampled data, and predicted data to be obtained. Simultaneously, the switchgear status can be evaluated based on both the sampled and predicted data, improving the accuracy of switchgear operating status predictions and enhancing electrical safety performance.

[0070] Embodiment 2 is the second embodiment of the present invention, which differs from the first two embodiments in that:

[0071] 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 and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0072] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0073] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be 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 processing in another suitable manner as necessary, and then stored in a computer memory.

[0074] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0075] Example 3, reference Figure 4 , which is the third embodiment of the present invention, provides a switch cabinet digital twin data analysis device, including a data acquisition module, a model building module, a data prediction module, a data calibration module and a state evaluation module.

[0076] The data acquisition module is used to obtain the operating status data of the switch cabinet. The operating status data includes electrical data information and environmental data information collected by sensors inside the switch cabinet.

[0077] The model building module is used to filter and integrate electrical data information and environmental data information, generate the operating status data of the switchgear, and establish a digital twin model of the switchgear based on the operating status data.

[0078] The data prediction module is used to obtain the predicted status data of the switchgear based on the switchgear digital twin model.

[0079] The data calibration module is used to obtain the predicted difference between the predicted state data and the operating state data within a preset sampling time, and to construct the associated parameters of each component in the switch cabinet based on the predicted difference.

[0080] The status assessment module is used to set the weight coefficients of each component in the switchgear, establish a switchgear operation status assessment model based on the associated parameters and weight coefficients, and input the predicted status data into the status assessment model to evaluate the operation status of the switchgear.

[0081] Furthermore, the data acquisition module is also used to collect electrical data information and environmental data information from sensors inside the switch cabinet; filter and integrate the electrical data information and environmental data information to generate operating status data of the switch cabinet.

[0082] Furthermore, the model building module is also used to establish a digital twin model of the switchgear based on the operating status data.

[0083] Furthermore, the data calibration module is also used to obtain the predicted difference between the predicted state data and the operating state data within a preset sampling time; calculate the adjustment mapping relationship of each component in the switch cabinet based on the predicted difference; and obtain the associated parameters of each component in the switch cabinet based on the adjustment mapping relationship.

[0084] Furthermore, the data calibration module is also used to obtain a first average value and a first standard deviation of the predicted state data within a preset sampling time, and to obtain a second average value and a second standard deviation of the operating state data within a preset sampling time; to determine whether the first standard deviation and the second standard deviation are within a preset deviation range; and if so, to calculate the difference between the first average value and the second average value as the predicted difference.

[0085] Furthermore, the data calibration module is also used to use the predicted difference to superimpose the predicted state data to generate adjustment data; and obtain the adjustment mapping relationship of each component in the switch cabinet through incremental learning based on the adjustment data within a preset sampling time.

[0086] Furthermore, the status assessment module is also used to set the weight coefficient of each component in the switch cabinet; based on the relationship between the associated parameters and the switch cabinet status, and combined with the weight coefficient, a switch cabinet operation status assessment model is established; and the predicted status data of the switch cabinet is input into the switch cabinet operation status assessment model to evaluate the operation status of the switch cabinet.

[0087] Furthermore, the status assessment module is also used to construct a historical query library based on the corresponding operating status obtained by inputting different predicted status data into the switch cabinet operating status assessment model; when obtaining the operating status data of the switch cabinet, it is determined whether it is included in the historical query library; if so, the status of the switch cabinet is determined to be the corresponding operating status in the historical query library.

[0088] The switchgear digital twin data analysis device provided in this application utilizes the switchgear digital twin data analysis method described in the aforementioned embodiments to address the technical issue of insufficient fault prediction accuracy during switchgear operation. Compared to the prior art, the switchgear digital twin data analysis device provided in this application achieves the same beneficial effects as the switchgear digital twin data analysis method described in the aforementioned embodiments, and the other technical features of the switchgear digital twin data analysis device are the same as those disclosed in the aforementioned embodiments.

[0089] 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 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 switchgear digital twin data analysis method, characterized by: include, Obtaining the operating status data of the switch cabinet, which includes electrical data information and environmental data information collected by sensors inside the switch cabinet; Filter and integrate electrical and environmental data to generate switchgear operating status data, and build a digital twin model of the switchgear based on the operating status data; Obtain predicted status data of the switchgear based on the switchgear digital twin model; Within a preset sampling time, the predicted difference between the predicted state data and the operating state data is obtained, and the associated parameters of each component in the switch cabinet are constructed based on the predicted difference; The weight coefficients of the components in the switchgear are set, and a switchgear operation status evaluation model is established based on the associated parameters and weight coefficients. The predicted status data is input into the status evaluation model to evaluate the operation status of the switchgear.

2. The switchgear digital twin data analysis method according to claim 1, characterized in that: The obtaining of the operating status data of the switch cabinet includes: Electrical and environmental data are collected by multiple sensors placed at key locations in the switch cabinet, and are uniformly encoded after time alignment to generate operating status data with timestamps.

3. The switchgear digital twin data analysis method according to claim 2, characterized in that: The associated parameters of each component in the switch cabinet are constructed, including: Within the preset sampling time, statistical analysis of the mean and standard deviation of the predicted status data and the operating status data is performed to determine whether the set deviation range conditions are met. If the conditions are met, associated parameters are constructed based on the mean value difference to describe the operating status deviation of each component.

4. The switchgear digital twin data analysis method according to claim 3, characterized in that: The evaluation of the operating status of the switchgear includes: The weight coefficients of the components in the switchgear are set, and an operation status assessment model is constructed based on the associated parameters and corresponding weights of each component. The predicted status data is input into the status assessment model, and the operation status level of the switchgear is output.

5. The switchgear digital twin data analysis method according to claim 4, characterized in that: The method of obtaining the predicted difference between the predicted state data and the operating state data, and constructing the associated parameters of each component in the switch cabinet based on the predicted difference, includes: Obtain the predicted difference between the predicted state data and the running state data within the preset sampling time; Calculate the adjustment mapping relationship of each component in the switchgear based on the predicted difference; Obtain associated parameters of each component in the switchgear according to the adjusted mapping relationship; The method of obtaining the predicted difference between the predicted state data and the running state data within the preset sampling time includes: Obtaining a first average value and a first standard deviation of the predicted state data within a preset sampling time, and obtaining a second average value and a second standard deviation of the operating state data within a preset sampling time; Determining whether the first standard deviation and the second standard deviation are within a preset deviation range; If it is within the preset deviation range, the difference between the first average value and the second average value is calculated and obtained as the predicted difference; The calculation of the adjustment mapping relationship of each component in the switch cabinet according to the predicted difference includes: Use the forecast difference to superimpose the forecast status data to generate adjustment data; The adjustment mapping relationship of each component in the switch cabinet is obtained through incremental learning based on the adjustment data within the preset sampling time.

6. The switchgear digital twin data analysis method according to claim 4, characterized in that: The predicted state data is input into the state evaluation model to evaluate the operating state of the switch cabinet, including: Set the weight coefficient of each component in the switchgear; Based on the relationship between the associated parameters and the switchgear status, and combined with the weight coefficient, a switchgear operation status evaluation model is established; The predicted state data of the switchgear is input into the switchgear operation state evaluation model to evaluate the operation state of the switchgear.

7. The switchgear digital twin data analysis method according to claim 4, characterized in that: The step of inputting the predicted state data into the state evaluation model to evaluate the operating state of the switch cabinet further includes: According to different prediction status data input into the switch cabinet operation status evaluation model, the corresponding operation status is obtained to build a historical query library; When obtaining the operating status data of the switch cabinet, determine whether it is included in the historical query library; If it is included in the historical query library, the state of the switch cabinet is determined to be the corresponding operating state in the historical query library.

8. A switch cabinet digital twin data analysis device, applying a switch cabinet digital twin data analysis method according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, model building module, data prediction module, data calibration module and status assessment module; The data acquisition module is used to obtain the operating status data of the switch cabinet, which includes electrical data information and environmental data information collected by sensors inside the switch cabinet; The model building module is used to filter and integrate the electrical data information and the environmental data information to generate the operating status data of the switchgear, and to establish a digital twin model of the switchgear based on the operating status data; The data prediction module is used to obtain the predicted state data of the switch cabinet based on the switch cabinet digital twin model; The data calibration module is used to obtain the predicted difference between the predicted state data and the operating state data within a preset sampling time, and to construct the associated parameters of each component in the switch cabinet based on the predicted difference; The state evaluation module is used to set the weight coefficient of each component in the switch cabinet, establish a switch cabinet operation state evaluation model based on the associated parameters and the weight coefficient, and input the predicted state data into the state evaluation model to evaluate the operation state of the switch cabinet.

9. 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 a switch cabinet digital twin data analysis method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a switch cabinet digital twin data analysis method according to any one of claims 1 to 7 are implemented.

Images