A fault diagnosis method, apparatus, system, device, and storage medium

Abstract

This invention discloses a fault diagnosis method, apparatus, system, device, and storage medium. The method includes: acquiring a determination time; determining the potential error of the device to be diagnosed and the deviation of the operating results of the digital twin system matched with the device to be diagnosed within the determination time; if the deviation of the operating results is greater than the potential error, then determining that the device to be diagnosed has a fault. The fault diagnosis method provided by this invention, by building a digital twin system matched with the device to be diagnosed, utilizes the potential error of the device to be diagnosed and the deviation of the operating results of the digital twin system matched with the device to be diagnosed for fault diagnosis, realizing automated fault diagnosis of the device to be diagnosed, reducing the dependence on the experience and ability of maintenance personnel, and by introducing potential error and determination time into the diagnosis, the probability of false alarms can be reduced.

Description

Technical Field

[0001] This invention relates to the field of new energy technology, and in particular to a fault diagnosis method, apparatus, system, equipment and storage medium. Background Technology

[0002] As new energy technologies receive increasing attention, more and more new energy systems (photovoltaics, wind power, hydrogen energy, energy storage, etc.) with different application scenarios have emerged. With the trend of systems becoming more complex, fault detection and operation and maintenance of system operation face more and more challenges.

[0003] Currently, the level of digitalization and intelligence in actual system operation and maintenance is limited. For example, in photovoltaic hydrogen production equipment, the detection of power generation performance often relies on horizontal comparison of unit power generation data to determine if there are any operational anomalies. However, for systems with complex terrain layouts, individual unit differences are significant, making horizontal comparisons difficult. Therefore, when individual devices malfunction, it is difficult to detect faults through machines, requiring a large number of experienced operation and maintenance personnel. This problem is even more pronounced for some remote, unattended large-scale photovoltaic power plants, or numerous and dispersed distributed photovoltaic systems, further delaying power generation and causing losses. Untimely repairs can even lead to more serious safety accidents. In photovoltaic hydrogen production equipment on the electricity consumption side, abnormal tank parameters and malfunctions in separators and other equipment may occur during actual operation, causing various problems, reducing system performance, and shortening equipment lifespan. However, it is difficult to identify and repair faults based solely on the experience of operation and maintenance personnel. Summary of the Invention

[0004] This invention provides a fault diagnosis method, apparatus, system, device, and storage medium to achieve automated fault diagnosis of the equipment to be diagnosed.

[0005] According to one aspect of the present invention, a fault diagnosis method is provided, comprising:

[0006] Get the judgment duration;

[0007] Determine the potential errors of the device under diagnosis and the deviations in the operating results of the digital twin system matched with the device under diagnosis within the determination time period;

[0008] If the deviation of the operating result is greater than the potential error, then the device to be diagnosed is determined to be faulty.

[0009] Furthermore, the device to be diagnosed includes a photovoltaic hydrogen production device.

[0010] Further, determining the potential errors of the device to be diagnosed within the determination time period includes:

[0011] Within the determination time period, obtain the sensor error of the device to be diagnosed and the model deviation of the digital twin system;

[0012] The potential error is determined based on the sensor error and the model deviation.

[0013] Further, determining the deviation in the operating results of the digital twin system matched with the device to be diagnosed within the determination time period includes:

[0014] Acquire real-time data of the device to be diagnosed and the digital twin system within the determination time period;

[0015] The deviation of the operating results is determined based on the real-time data of the device to be diagnosed and the digital twin system.

[0016] Furthermore, the digital twin system is constructed as follows:

[0017] Obtain the mechanism model constructed based on the principle of the device to be diagnosed, and the data model constructed based on the historical data of the device to be diagnosed;

[0018] The mechanistic model and the data model are then fused to obtain a fused model;

[0019] The fusion model is optimized to obtain the digital twin system.

[0020] Further, the fusion model is optimized to obtain the digital twin system, including:

[0021] Optimize the mechanism model in the fusion model, and use the output of the optimized mechanism model as the input of the data model;

[0022] Optimize the data model, and use the output of the optimized data model as the output of the fusion model;

[0023] The optimized fusion model is determined as the digital twin system.

[0024] Furthermore, optimizing the mechanistic model in the fusion model includes:

[0025] Obtain the first deviation of the mechanism model;

[0026] The mechanism model is optimized and a second deviation of the optimized mechanism model is obtained;

[0027] If the second deviation is less than the first deviation, the mechanism model optimization is complete; otherwise, return to the step of optimizing the mechanism model until the second deviation is less than the first deviation.

[0028] Furthermore, the data model is optimized, including:

[0029] Optimize the data model and obtain the third deviation of the optimized fusion model;

[0030] If the third deviation is less than the second deviation, the data model optimization is complete; otherwise, return to the step of optimizing the data model until the third deviation is less than the second deviation.

[0031] According to another aspect of the present invention, a fault diagnosis device is provided, comprising:

[0032] The judgment duration acquisition module is used to acquire the judgment duration;

[0033] The potential error and operational result deviation determination module is used to determine the potential error of the device to be diagnosed and the operational result deviation of the digital twin system matched with the device to be diagnosed within the determination time period.

[0034] The fault determination module is used to determine that the device to be diagnosed has a fault if the deviation of the operating result is greater than the potential error.

[0035] Optionally, the device to be diagnosed includes a photovoltaic hydrogen production device.

[0036] Optionally, the potential error and result deviation determination module is also used for:

[0037] Within the determination time period, obtain the sensor error of the device to be diagnosed and the model deviation of the digital twin system;

[0038] The potential error is determined based on the sensor error and the model deviation.

[0039] Optionally, the potential error and result deviation determination module is also used for:

[0040] Acquire real-time data of the device to be diagnosed and the digital twin system within the determination time period;

[0041] The deviation of the operating results is determined based on the real-time data of the device to be diagnosed and the digital twin system.

[0042] Optionally, the fault diagnosis device for the device under diagnosis further includes a digital twin system construction module for constructing the digital twin system, including:

[0043] The mechanism model and data model acquisition unit is used to acquire a mechanism model constructed based on the principle of the device to be diagnosed, and a data model constructed based on the historical data of the device to be diagnosed.

[0044] The fusion model acquisition unit is used to fuse the mechanism model and the data model to obtain a fusion model;

[0045] The fusion model optimization unit is used to optimize the fusion model to obtain the digital twin system.

[0046] Optionally, the fusion model optimization unit is also used for:

[0047] Optimize the mechanism model in the fusion model, and use the output of the optimized mechanism model as the input of the data model;

[0048] Optimize the data model, and use the output of the optimized data model as the output of the fusion model;

[0049] The optimized fusion model is determined as the digital twin system.

[0050] Optionally, the fusion model optimization unit is also used for:

[0051] Obtain the first deviation of the mechanism model;

[0052] The mechanism model is optimized and a second deviation of the optimized mechanism model is obtained;

[0053] If the second deviation is less than the first deviation, the mechanism model optimization is complete; otherwise, return to the step of optimizing the mechanism model until the second deviation is less than the first deviation.

[0054] Optionally, the fusion model optimization unit is also used for:

[0055] Optimize the data model and obtain the third deviation of the optimized fusion model;

[0056] If the third deviation is less than the second deviation, the data model optimization is complete; otherwise, return to the step of optimizing the data model until the third deviation is less than the second deviation.

[0057] According to another aspect of the present invention, a fault diagnosis system is provided, comprising:

[0058] The device to be diagnosed is used to provide real-time data of the device to be diagnosed.

[0059] A digital twin system is used to perform simulation calculations on the device to be diagnosed and to diagnose faults based on the potential errors of the device to be diagnosed and the deviations in the operating results of the digital twin system.

[0060] The digital twin system is matched with the device to be diagnosed, and communicates with the device to be diagnosed through an edge device installed on the device to be diagnosed to obtain real-time data of the device to be diagnosed, and runs on the edge device.

[0061] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0062] At least one processor; and

[0063] A memory communicatively connected to the at least one processor; wherein,

[0064] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the fault diagnosis method according to any embodiment of the present invention.

[0065] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the fault diagnosis method according to any embodiment of the present invention.

[0066] This invention first obtains the judgment time, then determines the potential error of the device to be diagnosed and the deviation of the operating results of the digital twin system matched with the device to be diagnosed within the judgment time. If the deviation of the operating results is greater than the potential error, then the device to be diagnosed is determined to be faulty. The fault diagnosis method provided by this invention, by building a digital twin system matched with the device to be diagnosed, utilizes the potential error of the device to be diagnosed and the deviation of the operating results of the digital twin system matched with the device to be diagnosed to perform fault diagnosis, realizing automated fault diagnosis of the device to be diagnosed, reducing the dependence on the experience and ability of maintenance personnel, and by introducing potential error and judgment time into the diagnosis, the probability of false alarms can be reduced.

[0067] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0068] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0069] Figure 1 This is a flowchart of a fault diagnosis method provided in Embodiment 1 of the present invention;

[0070] Figure 2 This is a flowchart illustrating a method for building a digital twin system according to Embodiment 1 of the present invention;

[0071] Figure 3 This is a flowchart of a model optimization method provided in Embodiment 1 of the present invention;

[0072] Figure 4 This is a flowchart of a fault diagnosis method provided according to Embodiment 2 of the present invention;

[0073] Figure 5 This is a flowchart of a fault diagnosis algorithm provided according to Embodiment 2 of the present invention;

[0074] Figure 6 This is a schematic diagram of the structure of a fault diagnosis device according to Embodiment 3 of the present invention;

[0075] Figure 7 This is a flowchart illustrating a deployment and operation mode of a digital twin system according to Embodiment 4 of the present invention;

[0076] Figure 8 This is a schematic diagram of the structure of an electronic device that implements the fault diagnosis method of Embodiment 5 of the present invention. Detailed Implementation

[0077] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0078] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0079] Example 1

[0080] Figure 1This is a flowchart of a fault diagnosis method provided in Embodiment 1 of the present invention. This embodiment is applicable to fault diagnosis of equipment to be diagnosed. The method can be executed by a fault diagnosis device and a fault diagnosis system. The fault diagnosis device can be implemented in hardware and / or software and can be configured in electronic equipment. Figure 1 As shown, the method includes:

[0081] S110, Obtain the judgment duration.

[0082] The determination time is a set period of time for determining the error of the diagnostic equipment and the digital twin system.

[0083] In this embodiment, the device to be diagnosed is the device used to diagnose its faults. The determination time can be set manually and can be determined according to system characteristics and requirements.

[0084] Optionally, the device to be diagnosed can be a photovoltaic hydrogen production device, which can be a device that uses new energy sources such as photovoltaics to electrolyze water to produce hydrogen.

[0085] Specifically, taking a photovoltaic hydrogen production equipment as an example, parameters such as the temperature of the electrolyzer in a photovoltaic hydrogen production equipment change slowly over time, allowing for a longer judgment period. Parameters such as the current change rapidly over time, allowing for a shorter judgment period. In the fault diagnosis logic, continuous monitoring based on the error within the judgment period can prevent false alarms caused by fluctuations in real-time data.

[0086] S120. Determine the potential errors of the device to be diagnosed and the deviations in the operating results of the digital twin system matched with the device to be diagnosed within the judgment period.

[0087] Digital twins fully utilize data such as physical models, sensor updates, and operational history to integrate simulation processes involving multiple disciplines, physical quantities, scales, and probabilities, completing mapping in virtual space to reflect the entire lifecycle of the corresponding physical equipment.

[0088] In this embodiment, the digital twin system matched with the device to be diagnosed is a simulation system obtained by simulating and mapping the device to be diagnosed. The digital twin system is a mirror image of the actual device to be diagnosed. It can acquire the data input collected in real time by the device to be diagnosed and perform real-time simulation calculations. The output of the digital twin system reflects the real-time output of the actual device to be diagnosed under normal conditions without any faults. Therefore, the actual device to be diagnosed can be diagnosed for faults based on the deviation of the operating results of the digital twin system.

[0089] Among them, the deviation of the operating results of the digital twin system is the deviation between the operating results of the digital twin system and the actual operating results of the device to be diagnosed, and the potential error of the device to be diagnosed is the allowable deviation that takes into account the model error brought about by the model results of the digital twin system and the measurement error brought about by the sensor measurement.

[0090] Optionally, when the digital twin system is running, the operating results generated by the digital twin system can be compared with the operating results of the actual device to be diagnosed to obtain the deviation of the operating results of the digital twin system. Then, the deviation can be compared with the potential error to achieve fault diagnosis.

[0091] S130. If the deviation of the operating result is greater than the potential error, then the equipment to be diagnosed is determined to be faulty.

[0092] In this embodiment, fault diagnosis of the device under test can be performed based on the deviation of the operating results and the potential error within the judgment period. Since the digital twin system is a mirror image of the actual device under test, the deviation of the operating results reflects the operating status of the device under test. The potential error is related to model error and measurement error, and can be considered as an unavoidable structural error rather than caused by device failure. Therefore, when the deviation of the operating results is greater than the potential error within the judgment period, the device under test can be considered to have failed, while when the deviation of the operating results is less than or equal to the potential error, it can be considered that no failure exists.

[0093] Furthermore, the construction method of the digital twin system is as follows: obtain a mechanism model constructed based on the principle of the device to be diagnosed, and a data model constructed based on the historical data of the device to be diagnosed; merge the mechanism model and the data model to obtain a fused model; optimize the fused model to obtain the digital twin system.

[0094] In this embodiment, the digital twin system of the device to be diagnosed can be composed of a combination of a mechanistic model and a data model. The mechanistic model is a precise mathematical model established based on the internal mechanisms of an object, a production process, or the transmission mechanism of material flow. The data model is formed by collecting massive amounts of data through mobile internet or other relevant software, organizing the data into information, integrating and refining the relevant information, and then training and fitting it based on the data to form an automated decision-making model. Both models can be established separately and then fused, and the fused model can be optimized to obtain a more accurate digital twin system.

[0095] Preferably, a mechanistic model and a data model can be built for each device module in the diagnostic equipment, and the models can be combined and optimized step by step to improve model accuracy. The advantages of different platforms can be utilized to build different models (such as mechanistic models and data models) and modules (such as optimization algorithms), and they can be run jointly on a unified platform to improve modeling and optimization efficiency. Taking a photovoltaic hydrogen production equipment as the diagnostic equipment as an example... Figure 2 This is a flowchart of a digital twin system construction method provided by an embodiment of the present invention. As shown in the figure, the specific steps of the construction process are as follows:

[0096] (1) Mechanism models were built on the Modelica platform for the support irradiation, photovoltaic modules, DC cables, DC voltage conversion, electrolyzer, and purification post-processing module in the photovoltaic hydrogen production equipment. Modelica is an open, object-oriented, equation-based computer language that can easily model complex physical systems across different fields, including mechanical, electronic, electrical, hydraulic, thermal, control, and process-oriented subsystem models.

[0097] (2) Test and verify the Modelica mechanism model, compare and verify the model simulation results with the actual data, record the deviation of the model results, and then encapsulate it into FMU (Functional Mock-up Unit) through the FMI (Functional Mock-up Interface) protocol for export. In this way, the existing unified protocol standard can be used to connect the languages ​​and operating methods of different platforms.

[0098] (3) In Python, the pyfmi library is used to build the FMU runtime environment and input model parameters, including simulation duration and step size, which can be directly set. Then, a neural network can be built using libraries such as PyTorch as the data model, and the activation function and number of hidden layers can be set. Finally, the final digital twin system is obtained through the model optimization process.

[0099] Optionally, the way to optimize the fusion model to obtain the digital twin system can be: optimizing the mechanistic model in the fusion model and using the output of the optimized mechanistic model as the input of the data model; optimizing the data model and using the output of the optimized data model as the output of the fusion model; and determining the optimized fusion model as the digital twin system.

[0100] Specifically, a step-by-step optimization approach can be adopted. First, optimize the mechanistic model, using its output as input to the data model, and then optimize the data model. Based on the FMU runtime environment built using the pyfmi library in Python, the FMU mechanistic model and data model can be connected within a unified Python runtime environment. Then, based on historical data from the actual system, the model can be distributed for optimization.

[0101] Optionally, the mechanism model in the fusion model can be optimized by: obtaining the first deviation of the mechanism model; optimizing the mechanism model and obtaining the second deviation of the optimized mechanism model; if the second deviation is less than the first deviation, the mechanism model optimization is completed; otherwise, return to the step of optimizing the mechanism model until the second deviation is less than the first deviation.

[0102] Specifically, the established mechanistic model is first compared and verified with historical data from the actual system to obtain the first deviation e1. Then, an optimization algorithm is used to optimize the internal parameters of the mechanistic model, such as the component characteristic parameters required in the component mechanistic model. These parameters may differ from the actual equipment due to batch quality deviations, deviations in experimental data provided by the manufacturer, etc., so optimization and correction are necessary. Preferably, optimization algorithms such as the SKO library or a self-built genetic algorithm can be used. If the second deviation e2 obtained after optimization is smaller than the deviation e1 before optimization, proceed to the next step; if it is larger than e1, return to execute a new round of optimization, and the optimization algorithm, optimization parameter range, and other settings can be modified in the new round of optimization.

[0103] Optionally, the data model can be optimized by: optimizing the data model and obtaining the third deviation of the optimized fusion model; if the third deviation is less than the second deviation, the data model optimization is complete; otherwise, return to the step of optimizing the data model until the third deviation is less than the second deviation.

[0104] Specifically, the output of the optimized mechanistic model is used as the input of the data model for fusion, and the data model is further optimized. The output of the fused model is compared and verified with the output data of the actual system to obtain the third deviation e3. The third deviation e3 is compared with the second deviation e2. If the deviation range is further reduced, the iterative optimization ends and a determined model is output; otherwise, a new round of data model optimization is performed, in which the hidden layers, activation functions, etc. of the data model can be adjusted.

[0105] Figure 3This is a flowchart of a model optimization method provided by an embodiment of the present invention. As shown in the figure, the historical measured input data x of the device to be diagnosed is input into the mechanism model. A first deviation e1 is calculated based on the output data y1 of the mechanism model and the historical measured output data y of the device to be diagnosed. Then, the mechanism model is optimized to obtain the output data y2 of the optimized mechanism model. A second deviation e2 is calculated based on the output data y2 of the optimized mechanism model and the historical measured output data y of the device to be diagnosed. If e2 ≥ e1, a new round of optimization is performed, and the optimization algorithm and parameter range can be modified in the new round of optimization. If e2 < e1, the output of the optimized mechanism model is used as the input of the data model for fusion, and the data model is optimized. The historical measured input data x of the device to be diagnosed is input into the fusion model, and a third deviation e3 is calculated based on the output data y3 of the fusion model and the historical measured output data y of the device to be diagnosed. If e3 < e2, the iterative optimization ends and a determined model is output; otherwise, it returns to execute a new round of data model optimization, in which the hidden layers, activation functions, etc. of the data model can be adjusted.

[0106] This invention first obtains the judgment time, then determines the potential error of the device to be diagnosed and the deviation of the operating results of the digital twin system matched with the device to be diagnosed within the judgment time. If the deviation of the operating results is greater than the potential error, then the device to be diagnosed is determined to be faulty. The fault diagnosis method provided by this invention, by building a digital twin system matched with the device to be diagnosed, utilizes the potential error of the device to be diagnosed and the deviation of the operating results of the digital twin system matched with the device to be diagnosed to perform fault diagnosis, realizing automated fault diagnosis of the device to be diagnosed, reducing the dependence on the experience and ability of maintenance personnel, and by introducing potential error and judgment time into the diagnosis, the probability of false alarms can be reduced. Furthermore, the digital twin system in this embodiment of the invention integrates a mechanistic model and a data model. Compared to a pure mechanistic model, it incorporates actual operational characteristic data, while compared to a pure data model, it increases the interpretability and scalability of the model and reduces its dependence on data. By using different platforms to build models separately and then achieving joint simulation under a unified platform in the construction of the twin system, the advantages and characteristics of different platforms can be utilized to efficiently build different types of models and modules. Moreover, by using a step-by-step optimization approach to first optimize the parameters of the mechanistic model and then further optimize the data model, the accuracy of the model can be effectively improved.

[0107] Example 2

[0108] Figure 4 This is a flowchart of a fault diagnosis method provided in Embodiment 2 of the present invention. This embodiment is a refinement of the above embodiment. Figure 4 As shown, the method includes:

[0109] S210, Obtain the judgment duration.

[0110] In this embodiment, the judgment duration can be manually set and determined according to system characteristics and requirements. For example, when the device to be diagnosed is a photovoltaic hydrogen production device, parameters such as the electrolyzer temperature change slowly over time, so a longer judgment duration can be set. Conversely, parameters such as current change rapidly over time, so a shorter judgment duration can be set. In the fault diagnosis logic, continuous monitoring based on the error within the judgment duration can prevent false alarms caused by fluctuations in real-time data.

[0111] S220. During the judgment period, obtain the sensor error of the device to be diagnosed and the model deviation of the digital twin system.

[0112] Among them, sensor error is the measurement accuracy error of the sensor, which can be obtained by referring to the value provided by the manufacturer; model deviation is the model deviation between the digital twin system after iterative optimization and the actual data of the device to be diagnosed, that is, the third deviation e3 in the above model optimization process.

[0113] Optionally, let measure_e represent the sensor error and model_e represent the model bias. The model bias can be calculated using the following formula:

[0114]

[0115] Where real_d is the actual data per second of the device to be diagnosed within a historical period, and the duration of this historical period is the judgment duration; model_d is the simulation result per second of the digital twin system within the same historical period; and n is the number of seconds of the judgment duration, which can be selected according to the characteristics of the device to be diagnosed and the fault point.

[0116] S230. Determine the potential error based on sensor error and model deviation.

[0117] Among them, potential error is a comprehensive consideration of sensor error and model bias within the judgment time.

[0118] Optionally, let potential_e represent the potential error, then the potential error can be calculated using the following formula:

[0119] potential_e=(1+model_e)*(1+measure_e)-1

[0120] S240. Acquire real-time data of the device to be diagnosed and the digital twin system within the determination time period.

[0121] In this embodiment, real-time data of the device to be diagnosed and the digital twin system can be obtained respectively within the determination time period based on their operating results.

[0122] S250. Determine the deviation of the operating results based on the real-time data of the device to be diagnosed and the digital twin system.

[0123] Among them, the deviation in operating results is the difference between the operating results of the digital twin system and the actual equipment to be diagnosed within the judgment period.

[0124] Optionally, let run_e represent the deviation of the running result, then the deviation of the running result can be calculated using the following formula:

[0125]

[0126] Where xi is the real-time operating result of the digital twin system, and yi is the real-time operating result of the device to be diagnosed.

[0127] S260. If the deviation of the operating result is greater than the potential error, then the equipment to be diagnosed is determined to be faulty.

[0128] In this embodiment, the simulation calculation data generated by the digital twin system during operation can be compared with the actual operating data of the device to be diagnosed, and a diagnosis can be made based on the deviation of the results. Potential errors are taken into account in the fault diagnosis logic, and a judgment period is given. An early warning is only generated when the deviation of the operating results exceeds the potential error within a certain period, thus preventing false warnings caused by fluctuations in real-time data.

[0129] Figure 5 This is a flowchart of a fault diagnosis algorithm provided in an embodiment of the present invention. As shown in the figure, the deviation of the running result run_e is determined based on the real-time data between the device to be diagnosed and the digital twin system. The potential error potential_e is determined based on the sensor error and the model deviation of the digital twin system within the judgment time. If run_e > potential_e, a fault warning is issued; otherwise, no warning is issued.

[0130] This invention first obtains the judgment time, then obtains the sensor error of the device under diagnosis and the model deviation of the digital twin system within the judgment time, then determines the potential error based on the sensor error and model deviation, then obtains the real-time data of the device under diagnosis and the digital twin system within the judgment time, and then determines the operational result deviation based on the real-time data of the device under diagnosis and the digital twin system. If the operational result deviation is greater than the potential error, then the device under diagnosis is determined to be faulty. The fault diagnosis method provided by this invention, by building a digital twin system matched with the device under diagnosis, uses the potential error of the device under diagnosis and the operational result deviation of the matching digital twin system to perform fault diagnosis, realizing automated fault diagnosis of the device under diagnosis, reducing the dependence on the experience and ability of maintenance personnel, and by introducing potential error and judgment time into the diagnosis, the probability of false alarms can be reduced.

[0131] Example 3

[0132] Figure 6 This is a schematic diagram of a fault diagnosis device provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes: a determination duration acquisition module 310, a potential error and operation result deviation determination module 320, and a fault determination module 330.

[0133] The determination duration acquisition module 310 is used to acquire the determination duration.

[0134] The potential error and operational result deviation determination module 320 is used to determine the potential error of the device to be diagnosed and the operational result deviation of the digital twin system matched with the device to be diagnosed within the determination time period.

[0135] Optionally, the equipment to be diagnosed includes photovoltaic hydrogen production equipment.

[0136] Optionally, the potential error and operational result deviation determination module 320 is also used for:

[0137] Obtain the sensor error of the device to be diagnosed and the model deviation of the digital twin system; determine the potential error based on the sensor error and model deviation.

[0138] Optionally, the potential error and operational result deviation determination module 320 is also used for:

[0139] Acquire real-time data from the device to be diagnosed and the digital twin system within the judgment period; determine the deviation of the operating results based on the real-time data from the device to be diagnosed and the digital twin system.

[0140] The fault determination module 330 is used to determine that the equipment to be diagnosed has a fault if the deviation of the running result is greater than the potential error.

[0141] Optionally, the fault diagnosis device also includes a digital twin system construction module 340 for constructing a digital twin system, including: a mechanism model and data model acquisition unit 341, a fusion model acquisition unit 342, and a fusion model optimization unit 343.

[0142] Mechanism model and data model acquisition unit 341 is used to acquire the mechanism model constructed based on the principle of the device to be diagnosed, and the data model constructed based on the historical data of the device to be diagnosed.

[0143] The fusion model acquisition unit 342 is used to fuse the mechanism model and the data model to obtain a fusion model.

[0144] The fusion model optimization unit 343 is used to optimize the fusion model to obtain a digital twin system.

[0145] Optionally, the fusion model optimization unit 343 is also used for:

[0146] Optimize the mechanistic model in the fusion model, and use the output of the optimized mechanistic model as the input of the data model; optimize the data model, and use the output of the optimized data model as the output of the fusion model; determine the optimized fusion model as a digital twin system.

[0147] Optionally, the fusion model optimization unit 343 is also used for:

[0148] Obtain the first deviation of the mechanism model; optimize the mechanism model and obtain the second deviation of the optimized mechanism model; if the second deviation is less than the first deviation, the mechanism model optimization is complete; otherwise, return to the step of optimizing the mechanism model until the second deviation is less than the first deviation.

[0149] Optionally, the fusion model optimization unit 343 is also used for:

[0150] Optimize the data model and obtain the third deviation of the optimized fusion model; if the third deviation is less than the second deviation, the data model optimization is complete; otherwise, return to the step of optimizing the data model until the third deviation is less than the second deviation.

[0151] The fault diagnosis device provided in the embodiments of the present invention can execute the fault diagnosis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0152] Example 4

[0153] This invention provides a fault diagnosis system, comprising:

[0154] The device to be diagnosed, used to provide real-time data of the device to be diagnosed;

[0155] A digital twin system is used to perform simulation calculations on the equipment to be diagnosed and to diagnose faults based on the potential errors of the equipment and the deviations in the operating results of the digital twin system.

[0156] The digital twin system is matched with the device to be diagnosed. It communicates with the device to be diagnosed through an edge device installed on the device to obtain real-time data from the device to be diagnosed and runs on the edge device.

[0157] In this embodiment, for an existing device to be diagnosed, it can be modified to deploy the digital twin system described in this application for fault diagnosis. Specifically, an edge device needs to be installed in the actual device to be diagnosed. The edge device can communicate and interact with the device's own SCADA system. Then, the determined digital twin system is converted into an image and deployed on the edge device using a Docker container. Because Docker containers contain a runtime environment and executable programs, they can be used directly across platforms and hosts.

[0158] Figure 7 This is a flowchart of a digital twin system deployment and operation mode provided by an embodiment of the present invention. As shown in the figure, the digital twin system uses real-time collected data input, such as meteorological data, to perform real-time simulation calculations, and uses the above-mentioned fault diagnosis algorithm to perform fault diagnosis based on the real-time output data of the device to be diagnosed, thereby determining whether to issue an early warning.

[0159] The fault diagnosis system provided in this embodiment of the invention can execute the fault diagnosis method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0160] Example 5

[0161] Figure 8 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0162] like Figure 8As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0163] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0164] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as fault diagnosis methods.

[0165] In some embodiments, the fault diagnosis method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the fault diagnosis described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the fault diagnosis method by any other suitable means (e.g., by means of firmware).

[0166] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0167] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0168] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0169] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0170] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0171] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0172] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0173] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A failure diagnosis method characterized by comprising: The method comprises the following steps: acquiring a determination duration; acquiring a sensor error of a to-be-diagnosed device and a model deviation of a digital twin system within the determination duration, determining a potential error of the to-be-diagnosed device according to the sensor error and the model deviation; determining a running result deviation of the digital twin system matched with the to-be-diagnosed device within the determination duration; wherein the model deviation is determined according to the following formula: wherein, is actual data per second of the to-be-diagnosed device in a historical time, a length of the historical time is a determination length, is simulation result per second of the digital twin system in the historical time, n is a number of seconds of the determination length, and the determination length is determined according to the to-be-diagnosed device and a fault point characteristic. the potential error is determined according to the following formula: wherein, is the sensor error, is the potential error; the running result deviation is determined according to the following formula: wherein, is the running result deviation of the digital twin system, is the real-time running result of the digital twin system, is the real-time running result of the equipment to be diagnosed; if the running result deviation is greater than the potential error, it is determined that the to-be-diagnosed device has a fault.

2. The method of claim 1, wherein, The to-be-diagnosed device comprises a photovoltaic hydrogen production device.

3. The method of claim 1, wherein, The digital twin system is constructed in the following manner: acquiring a mechanism model constructed according to the principle of the to-be-diagnosed device and a data model constructed according to historical data of the to-be-diagnosed device; fusing the mechanism model and the data model to acquire a fused model; optimizing the fused model to obtain the digital twin system.

4. The method of claim 3, wherein, Optimizing the fused model to obtain the digital twin system comprises: optimizing the mechanism model in the fused model, taking the output of the optimized mechanism model as the input of the data model; optimizing the data model, taking the output of the optimized data model as the output of the fused model; taking the optimized fused model as the digital twin system.

5. The method of claim 4, wherein, Optimizing the mechanism model in the fused model comprises: acquiring a first deviation of the mechanism model; optimizing the mechanism model to obtain a second deviation of the optimized mechanism model; if the second deviation is less than the first deviation, the optimization of the mechanism model is completed, otherwise, returning to execute the step of optimizing the mechanism model until the second deviation is less than the first deviation.

6. The method of claim 5, wherein, Optimizing the data model comprises: optimizing the data model to acquire a third deviation of the optimized fused model; if the third deviation is less than the second deviation, the optimization of the data model is completed, otherwise, returning to execute the step of optimizing the data model until the third deviation is less than the second deviation.

7. A failure diagnosing apparatus characterized by comprising: The method comprises the following steps: a determination duration acquisition module is configured to acquire a determination duration; a potential error and running result deviation determination module is configured to acquire a sensor error of a to-be-diagnosed device and a model deviation of a digital twin system within the determination duration, determine a potential error of the to-be-diagnosed device according to the sensor error and the model deviation, and determine a running result deviation of the digital twin system matched with the to-be-diagnosed device within the determination duration; wherein the model deviation is determined according to the following formula: wherein, is actual data per second of the to-be-diagnosed device in a historical time, a length of the historical time is a determination length, is simulation result per second of the digital twin system in the historical time, n is a number of seconds of the determination length, and the determination length is determined according to the to-be-diagnosed device and a fault point characteristic. the potential error is determined according to the following formula: wherein, is the sensor error, is the potential error; the running result deviation is determined according to the following formula: wherein, is the operation result deviation of the digital twin system, is the real-time operation result of the digital twin system, is the real-time operation result of the equipment to be diagnosed; a fault determination module is configured to determine that the to-be-diagnosed device has a fault if the running result deviation is greater than the potential error.

8. A failure diagnosis system characterized by comprising: The method comprises the following steps: a to-be-diagnosed device is configured to provide real-time data of the to-be-diagnosed device; The digital twin system is used for simulating calculation on the to-be-diagnosed equipment and performing fault diagnosis according to potential errors of the to-be-diagnosed equipment and running result deviation of the digital twin system; wherein, the determination method of the potential errors of the to-be-diagnosed equipment comprises: acquiring sensor errors of the to-be-diagnosed equipment and model deviation of the digital twin system within a judgment duration, and determining the potential errors of the to-be-diagnosed equipment according to the sensor errors and the model deviation; Wherein, the digital twin system is matched with the to-be-diagnosed equipment, communicates with the to-be-diagnosed equipment through an edge device installed on the to-be-diagnosed equipment, acquires real-time data of the to-be-diagnosed equipment, and runs on the edge device; The model deviation is determined according to the following formula: wherein, is actual data per second of the to-be-diagnosed device in a historical time, a length of the historical time is a determination length, is simulation result per second of the digital twin system in the historical time, n is a number of seconds of the determination length, and the determination length is determined according to the to-be-diagnosed device and a fault point characteristic. The potential errors are determined according to the following formula: wherein, is the sensor error, is the potential error; The running result deviation is determined according to the following formula: wherein, is the running result deviation of the digital twin system, is the real-time running result of the digital twin system, is the real-time running result of the equipment to be diagnosed.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the fault diagnosis method in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the fault diagnosis method in any one of claims 1-6 when executed.

Images