Heat supply system fault detection method, device, equipment, storage medium and product

Abstract

The invention relates to a heat supply system fault detection method and device, equipment, a storage medium and a product. The method comprises the steps that multi-dimensional historical transient operation data of a target heat supply system within a preset time period is acquired; according to the operation time sequence characteristics of the multi-dimensional historical transient operation data, fitting the multi-dimensional historical transient operation data to obtain multi-dimensional historical steady-state operation data reflecting the change of the operation condition of the target heat supply system along with time; according to the multi-dimensional historical steady-state operation data, a fault detection model of the target heat supply system is constructed, and the fault detection model is used for detecting the operation condition of the target heat supply system along with time change; and performing fault detection on the target heat supply system according to the fault detection model. By adopting the method, the detection accuracy of heat supply system fault detection is improved.

Description

Technical Field

[0001] The present application relates to the field of smart heating technology, and in particular to a heating system fault detection method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] With the continuous development of science and technology, in order to improve energy efficiency and enhance user experience, in the field of smart heating, comprehensive heating systems have gradually replaced heating systems with single heating modes and become the mainstream solution in the market. For example, park heating adopts an unattended heating system that has both park steam supply and high-temperature water heating. At the same time, it is very necessary to detect the operating status of the heating system or the abnormal operating conditions of the heating system.

[0003] At present, in the process of heating system fault detection, experienced process personnel or engineers are usually relied on for fault detection. However, since the fault diagnosis through human qualitative analysis is easily affected by subjective factors and lacks effective data support, the obtained fault detection results cannot reflect the actual operation of the heating system, which makes it easy for the heating system to malfunction or consume a lot of energy. Therefore, the current detection accuracy of heating system fault detection is low. Summary of the invention

[0004] Based on this, it is necessary to provide a heating system fault detection method, device, computer equipment, computer-readable storage medium and computer program product to improve the detection accuracy of heating system fault detection in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for detecting a fault in a heating system, the method comprising:

[0006] Obtain multi-dimensional historical transient operation data of the target heating system within a preset time period;

[0007] According to the operation timing characteristics of the multidimensional historical transient operation data, the multidimensional historical transient operation data is fitted to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing over time;

[0008] Constructing a fault detection model of the target heating system according to the multi-dimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes over time;

[0009] According to the fault detection model, fault detection is performed on the target heating system.

[0010] In one embodiment, the step of obtaining multi-dimensional historical transient operation data of the target heating system within a preset time period includes:

[0011] Acquire a plurality of historical transient operation data of the target heating system provided by different data sources within the preset time period;

[0012] The transient operation data are fused according to the performance impact weights corresponding to the historical transient operation data to obtain the multi-dimensional historical transient operation data.

[0013] In one of the embodiments, the multidimensional historical transient operation data is fitted according to the operation sequence characteristics of the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing over time, including:

[0014] According to the operation timing characteristics of the multi-dimensional historical transient operation data, the multi-dimensional historical transient operation data is divided into transient operation training data and transient operation test data;

[0015] Performing operation timing alignment on the transient operation training data and the transient operation test data, and using the transient operation training data and the transient operation test data after the operation timing alignment as a plurality of transient operation data to be fitted;

[0016] According to the correlation between the transient operation data to be fitted, each transient operation data to be fitted is fitted into the multi-dimensional historical steady-state operation data.

[0017] In one embodiment, the step of aligning the transient operation training data and the transient operation test data in terms of operation timing includes:

[0018] Determining a timing lag coefficient of the target heating system according to an operation timing deviation between the transient operation training data and the transient operation test data;

[0019] The transient operation training data and the transient operation test data are aligned in operation timing according to the timing lag coefficient.

[0020] In one embodiment, constructing a fault detection model of the target heating system according to the multi-dimensional historical steady-state operation data includes:

[0021] Performing double noise reduction on the multi-dimensional historical steady-state operation data to obtain first steady-state operation data and second steady-state operation data under different noise reduction dimensions;

[0022] Extracting features from the first steady-state operation data and the second steady-state operation data respectively to obtain a first steady-state operation feature and a second steady-state operation feature;

[0023] A fault detection model of the target heating system is constructed according to the target steady-state operation characteristics formed by integrating the first steady-state operation characteristics and the second steady-state operation characteristics.

[0024] In one embodiment, performing fault detection on the target heating system according to the fault detection model includes:

[0025] Detecting the real-time health of the target heating system according to the fault detection model;

[0026] When it is detected that the real-time health status is less than a preset health status threshold, a fault type detection is performed on the target heating system according to the real-time health status.

[0027] In a second aspect, the present application also provides a heating system fault detection device, comprising:

[0028] An acquisition module, used to acquire multi-dimensional historical transient operation data of a target heating system within a preset time period;

[0029] A fitting module, for fitting the multidimensional historical transient operation data according to the operation timing characteristics of the multidimensional historical transient operation data, to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing with time;

[0030] A construction module, used to construct a fault detection model of the target heating system according to the multi-dimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes over time;

[0031] A detection module is used to perform fault detection on the target heating system according to the fault detection model.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Acquire multidimensional historical transient operation data of a target heating system within a preset time period; fit the multidimensional historical transient operation data according to the operation sequence characteristics of the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system that changes with time; construct a fault detection model for the target heating system according to the multidimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes with time; perform fault detection on the target heating system according to the fault detection model.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0035] Acquire multidimensional historical transient operation data of a target heating system within a preset time period; fit the multidimensional historical transient operation data according to the operation sequence characteristics of the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system that changes with time; construct a fault detection model for the target heating system according to the multidimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes with time; perform fault detection on the target heating system according to the fault detection model.

[0036] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0037] Acquire multidimensional historical transient operation data of a target heating system within a preset time period; fit the multidimensional historical transient operation data according to the operation sequence characteristics of the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system that changes with time; construct a fault detection model for the target heating system according to the multidimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes with time; perform fault detection on the target heating system according to the fault detection model.

[0038] The above-mentioned heating system fault detection method, device, computer equipment, computer-readable storage medium and computer program product first obtain the multidimensional historical transient operation data of the target heating system within a preset time period, and then fit the multidimensional historical transient operation data through the operation sequence characteristics of the multidimensional historical transient operation data to obtain the multidimensional historical steady-state operation data of the target heating system's operation status changing with time, that is, by comprehensively processing the multidimensional historical transient operation data of the target heating system within a preset time period, the multidimensional historical steady-state operation data reflecting the continuous operation status changes of the target heating system within the preset time period is obtained, and then with the help of the multidimensional historical steady-state operation data, a fault detection model for detecting the operation status of the target heating system changing with time is constructed, and finally based on the fault detection Model is used to detect faults in the target heating system. Since the multi-dimensional historical steady-state operation data can reflect the changes in the continuous operation status of the heating system during operation from different dimensions, the fault detection model constructed by the multi-dimensional historical steady-state operation data can accurately detect the operation status of the target heating system that changes over time with the support of data, rather than relying only on human subjective detection when detecting heating system faults. Therefore, the technical defects of human qualitative fault diagnosis that is easily affected by subjective factors and lacks effective data support, resulting in the inability of the obtained fault detection results to reflect the actual operation status of the heating system, which makes it easy for the heating system to fail to operate or the heating system to consume a lot of energy, etc., are overcome. Therefore, the detection accuracy of heating system fault detection is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 It is a schematic flow chart of a method for detecting a fault in a heating system in one embodiment;

[0041] Figure 2 A schematic diagram of a flow chart of a method for detecting a failure of a heating system in another embodiment;

[0042] Figure 3 is a structural block diagram of a heating system fault detection device in one embodiment;

[0043] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] First of all, it should be understood that in a comprehensive heating system, there are large differences in the operating processes of different heating methods. Taking the park heating system as an example, there are relatively large differences in the operating processes of park steam supply and high-temperature water heating. High-temperature water heating is more oriented towards centralized heating for residents, and high-temperature water heating is a system with large inertia and large lag, while the heating objects of park steam supply are more oriented towards various enterprises in industrial parks. The pipe size, temperature resistance, thermal inertia and transmission distance of their steam pipe networks are obviously different. In other words, the data reflecting the operation status of the heating system in a comprehensive heating system are complex and huge. In order to avoid the previous detection method that relies on manual qualitative detection of heating system faults and accurately detect heating system faults, it is necessary to integrate and analyze various data and explore the relationship between data. That is, there is an urgent need for a heating system fault detection method that improves the detection accuracy of heating system fault detection.

[0046] In one embodiment, Figure 1As shown, a heating system fault detection method is provided. This embodiment takes the method applied to a terminal as an example. It can be understood that the terminal can execute the heating system fault detection method through a deployed heating system fault detection system. The terminal includes but is not limited to a personal computer, a laptop computer, a smart phone, and a tablet computer. The terminal includes an acquisition module, a fitting module, a construction module, and a detection module. The acquisition module is used to acquire multidimensional historical transient operation data of a target heating system within a preset time period. The fitting module is used to fit the multidimensional historical transient operation data according to the operating sequence characteristics of the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data of the target heating system that changes with time. The construction module is used to construct a fault detection model of the target heating system according to the multidimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation of the target heating system that changes with time, and the detection model is used to detect the operation of the target heating system that changes with time. According to the fault detection model, the target heating system is subjected to fault detection, that is, through the information interaction between the acquisition module, the fitting module, the construction module and the detection module, firstly, the operation sequence characteristics of the multi-dimensional historical transient operation data of the target heating system within the preset time period are used to fit the multi-dimensional historical transient operation data to obtain the multi-dimensional historical steady-state operation data, and then through the multi-dimensional historical steady-state operation data, a fault detection model for detecting the operation status of the target heating system that changes with time can be constructed, and finally, the target heating system is subjected to fault detection through the fault detection model, so that the purpose of objectively detecting the fault of the target heating system under the support of data can be achieved, so there is no need to rely on human subjective detection, so the detection accuracy of the heating system fault detection is improved, it can be understood that the method can also be applied to the server, and can also be applied to the system including the terminal and the server, and is realized through the interaction between the terminal and the server. In this embodiment, the method includes the following steps 202 to 208. Among them:

[0047] Step 202: Acquire multi-dimensional historical transient operation data of the target heating system within a preset time period.

[0048] It should be noted that the heating system fault detection system can periodically collect operating data related to the operating conditions of the target heating system that change over time, and obtain multi-dimensional historical transient operating data of the target heating system within a preset time period by fusing and analyzing the relevant operating data, wherein the time period length of the preset time period can be set by the user according to the detection requirements. For example, the preset time period can be one day, one hour or 30 minutes, etc. The multi-dimensional historical transient operating data refers to the historical transient operating data under multiple operating condition influencing dimensions, and reflects the instantaneous operating conditions of the target heating system. The historical transient operating data refers to the data of the instantaneous operating status of the heating system caused by factors such as load changes or equipment failures within a certain time period.

[0049] It should be noted that the multi-dimensional historical transient operation data can reflect the results of comprehensive collection of the heating parameters of the target heating system. The historical transient operation data may specifically include automatic control instrument data (temperature, pressure, flow, heat, electric adjustment execution opening / feedback opening, current, electricity, liquid level, variable frequency pump frequency, make-up water pump frequency and switch quantity, etc.), user room temperature data, weather forecast data, real-time temperature data, heat source data (temperature, flow, pressure and heat, etc.), household charging data and customer service complaint work order data, etc. After collecting the above data, the historical transient operation data can be subjected to multi-dimensional statistical analysis based on big data or expert models, thereby obtaining multi-dimensional historical transient operation data.

[0050] As an example, a plurality of historical transient operation data of a target heating system within a preset time period is obtained, and each historical transient operation data is integrated into multi-dimensional historical transient operation data.

[0051] Step 204 , fitting the multidimensional historical transient operation data according to the operation sequence characteristics of the multidimensional historical transient operation data, and obtaining multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing with time.

[0052] It should be noted that since the multi-dimensional historical transient operation data reflects the instantaneous operating status of the target heating system at a certain moment within a preset time period, and the failure of the target heating system occurs under continuous operation, it is difficult to accurately reflect the changes in the operating conditions of the target heating system over time within a certain time period through the multi-dimensional historical transient operation data. Therefore, it is necessary to further process the multi-dimensional historical transient operation data to obtain multi-dimensional historical steady-state operation data that reflects the changes in the operating conditions of the target heating system over time. Among them, the multi-dimensional historical steady-state operation data refers to the operation data composed of historical transient operation data under multiple operating condition influencing dimensions, which reflects the continuous operation of the target heating system. The operation timing characteristics are used to characterize the operation timing of the multi-dimensional historical transient operation data.

[0053] As an example, step 204 includes: extracting the operation sequence characteristics of the multidimensional historical transient operation data, performing linear fitting on the multidimensional historical transient operation data, and obtaining multidimensional historical steady-state operation data of the operation status of the target heating system that changes with time.

[0054] Step 206: construct a fault detection model of the target heating system based on the multi-dimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes over time.

[0055] It should be noted that the fault detection model is used to detect the operation status of the target heating system over time, and can be obtained by iteratively training a preset fault detection model based on a large amount of multi-dimensional historical steady-state operation data, wherein the preset fault detection model can be specifically a neural network model. For example, in one feasible method, assuming that the heating system is a comprehensive park heating system, a plurality of historical transient operation data within a preset time period provided by a heating heat exchange station and a steam heat exchange station are used, and then pre-processing, data fusion, and preset analysis models are performed on the historical transient operation data to obtain The multi-dimensional historical steady-state operation data reflecting the operation status of the target heating system changing over time can be obtained, and finally the fault detection model constructed through the multi-dimensional historical steady-state operation data can accurately identify the abnormal heating condition of the target heating system, and diagnose the operating condition operation diagnosis and equipment fault diagnosis of the heating heat exchange station and the steam heat exchange station. It can be understood that the fault detection model constructed in the above manner can obtain 10%~20% energy-saving and consumption reduction effects and reduce the operation failure rate of the heating heat exchange station and the steam heat exchange station after fault detection and diagnosis debugging of the heating heat exchange station and the steam heat exchange station.

[0056] As an example, step 206 includes: inputting multi-dimensional historical steady-state operation data into a preset fault detection model, iteratively training the preset fault detection model, and using the iteratively completed preset fault detection model as a fault detection model of the target heating system.

[0057] Step 208: Perform fault detection on the target heating system according to the fault detection model.

[0058] As an example, step 208 includes: performing fault detection on the target heating system by inputting multi-dimensional real-time operation data of the target heating system into a fault detection model.

[0059] In the above-mentioned heating system fault detection method, firstly, a plurality of historical transient operation data of the target heating system within a preset time period are obtained, and the plurality of historical transient operation data are integrated into multidimensional historical transient operation data, and then the multidimensional historical transient operation data are fitted through the operation sequence characteristics of the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing with time, and a preset fault detection model is iteratively trained through the multidimensional historical steady-state operation data, and the preset fault detection model after the iteration is used as the fault detection model of the target heating system, and finally the target heating system is subjected to real-time fault detection through the fault detection model. Since the multidimensional historical steady-state operation data can It can reflect the changes in the continuous operation of the heating system during operation from different dimensions, and then rely on the fault detection model constructed by multi-dimensional historical steady-state operation data. It can accurately detect the operation status of the target heating system that changes over time with the support of data, rather than relying only on human subjective detection when detecting heating system faults. Therefore, it overcomes the technical defects that the fault diagnosis through human qualitative analysis is easily affected by subjective factors and lacks effective data support, resulting in the failure of the obtained fault detection results to reflect the actual operation of the heating system, which makes it easy for the heating system to fail to operate or the heating system to consume a lot of energy. Therefore, the detection accuracy of heating system fault detection is improved.

[0060] In one embodiment, Figure 2 As shown, the multi-dimensional historical transient operation data of the target heating system within a preset time period is obtained, including:

[0061] Step 302: Acquire a plurality of historical transient operation data of the target heating system provided by different data sources within a preset time period.

[0062] It should be noted that since the sources of historical transient operation data under different influencing dimensions that affect the operation of the target heating system are different, in order to comprehensively evaluate the historical operation of the target heating system, it is necessary to extract multi-dimensional historical transient operation data from different data sources. For example, in one feasible method, the different data sources can specifically be a heating network monitoring system, an Internet of Things room temperature system, a weather forecast system, and a customer service charging system.

[0063] As an example, step 302 includes: obtaining a plurality of historical transient operation data of the target heating system provided by the heating network monitoring system, the Internet of Things room temperature system, the weather forecast system and the customer service charging system within a preset time period.

[0064] Step 304 , according to the performance impact weight corresponding to each historical transient operation data, each transient operation data is integrated to obtain multi-dimensional historical transient operation data.

[0065] It should be noted that since the historical transient operation data provided by different data sources have different degrees of impact on the operating performance of the target heating system, by configuring different performance impact weights for the historical transient operation data from different sources, it is possible to obtain multi-dimensional historical transient operation data that accurately feedback the instantaneous operating conditions of the target heating system within a preset time period. For example, in one feasible method, assuming that the historical transient operation data a comes from system A, the historical transient operation data b comes from system B, and the historical transient operation data c comes from system C, then the performance impact weights of 0.5, 0.3 and 0.2 can be configured for systems A, B and C respectively, so that the fusion of the historical transient operation data is ultimately completed relying on the performance impact weights.

[0066] As an example, step 304 includes: obtaining the performance impact weight corresponding to each historical transient operation data, and performing weighted fusion on each transient operation data based on the performance impact weight to obtain multi-dimensional historical transient operation data.

[0067] In this embodiment, in the process of acquiring multi-dimensional historical transient operation data, it is taken into account that the historical transient operation data from different data sources have different degrees of influence on the operating performance of the target heating system. In the process of pre-processing the historical transient operation data to obtain the multi-dimensional historical transient operation data, different performance impact weights are configured for different historical transient operation data. Finally, through different performance impact weights, each transient operation data is weightedly fused to obtain multi-dimensional historical transient operation data, thereby ensuring the objective feedback of the multi-dimensional historical transient operation data on the operating conditions of the target heating system. Therefore, the foundation is laid for improving the detection accuracy of heating system fault detection.

[0068] In one embodiment, according to the operation sequence characteristics of the multidimensional historical transient operation data, the multidimensional historical transient operation data is fitted to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing with time, including:

[0069] According to the operation timing characteristics of the multidimensional historical transient operation data, the multidimensional historical transient operation data are divided into transient operation training data and transient operation test data; the operation timing of the transient operation training data and the transient operation test data are aligned, and the transient operation training data and the transient operation test data after the operation timing alignment are used together as a plurality of transient operation data to be fitted; according to the correlation relationship between each transient operation data to be fitted, each transient operation data to be fitted is fitted into the multidimensional historical steady-state operation data.

[0070] It should be noted that since the heating system can be regarded as an inertial system, and there is a time lag between the relative downstream and the relative upstream in a certain link of the inertial system, before the final fitting is performed to obtain the multi-dimensional historical steady-state operation data, it is necessary to eliminate the non-corresponding relationship between the transient and steady states of the system caused by the lag of physical transmission, and to advance the downstream data in appropriate time sequence to ensure scientific steady-state fitting. Among them, the transient operation training data refers to the upstream data, and the transient operation test data refers to the downstream data. That is, before fitting to obtain the multi-dimensional historical steady-state operation data, the transient operation training data and the transient operation test data can be formed in a preset proportion according to the operating time characteristics of the multi-dimensional historical transient operation data. It can be understood that the multi-dimensional historical transient operation data such as transient operation training data and transient operation test data can all be operating data of the heating system in a healthy state during the historical operation cycle.

[0071] As an example, according to the operation timing characteristics of multidimensional historical transient operation data, the operation time points of the multidimensional historical transient operation data are detected, and the multidimensional historical transient operation data with an operation time point less than a preset operation time point threshold is used as transient operation training data, and the multidimensional historical transient operation data with an operation time point greater than or equal to the preset operation time point threshold is used as transient operation test data; according to the operation timing deviation between the transient operation training data and the transient operation test data, the transient operation training data and the transient operation test data are aligned in operation timing, and the transient operation training data and the transient operation test data after the operation timing alignment are used together as multiple transient operation data to be fitted; based on the preset binary decoupling fitting method, each transient operation data to be fitted is fitted to obtain multidimensional historical steady-state operation data.

[0072] In one feasible manner, the preset two-dimensional decoupling fitting method can be specifically as follows: using "atmospheric temperature", "primary heating" and "primary flow supply" as transient operation training data, and fitting with the transient operation test data "secondary heating" after time sequence dislocation, so as to obtain multi-dimensional historical steady-state operation data. It can be understood that the fitted multi-dimensional historical steady-state operation data can be used for prediction and fault warning.

[0073] In this embodiment, taking into account the non-corresponding relationship between the transient operation and the steady-state network operation of the heating system, the multi-dimensional historical transient operation data is first divided based on the operation timing characteristics of the multi-dimensional historical transient operation data to obtain transient operation training data and transient operation test data, and then the transient operation training data and the transient operation test data are time-aligned by adopting the timing misalignment method. Finally, after the timing alignment is completed, the multivariate quadratic decoupling fitting method is used to fit multiple transient operation data to be fitted to obtain multi-dimensional historical steady-state operation data. Therefore, the non-corresponding relationship between the transient operation and the steady-state operation inside the heating system is eliminated through timing processing, thereby improving the fitting accuracy of the multi-dimensional historical steady-state operation data obtained by fitting.

[0074] In one embodiment, performing operation timing alignment on transient operation training data and transient operation test data includes:

[0075] According to the operation timing deviation between the transient operation training data and the transient operation test data, the timing lag coefficient of the target heating system is determined; according to the timing lag coefficient, the operation timing of the transient operation training data and the transient operation test data is aligned.

[0076] It should be noted that, for heating systems with large inertia, a unified timing misalignment method can be used to align the transient operation training data and the transient operation test data, that is, the timing lag coefficient between the upstream and downstream physical quantities of each subsystem of the heating system is calculated through the root mean square of the timing misalignment, and finally the operation timing calibration of the transient operation training data and the transient operation test data is completed. For example, in one feasible method, there is a timing lag between the relative downstream and the relative upstream in a certain link of the heating system. Before performing the correlation and support fitting between the data, it is necessary to eliminate the non-corresponding relationship between the transient and steady states of the heating system caused by the lag of physical transmission, and to advance the downstream data in appropriate timing.

[0077] As an example, the operation timing deviation between the transient operation training data and the transient operation test data is solved by preset minimum root mean square algorithm, and the timing lag coefficient of the target heating system is determined according to the operation timing deviation; the operation timing of the transient operation training data and the transient operation test data is calibrated by the timing lag coefficient.

[0078] In one practicable manner, assuming that the transient operation training data is A and the transient operation test data is B, firstly, the transient operation training data A and the transient operation test data B are preprocessed to obtain the preprocessed transient operation training data A1 and the preprocessed transient operation test data B1, and further, the preset minimum mean square root algorithm is initialized, for example, the learning rate and the filter order of the minimum mean square root algorithm are initialized, and then the data B1 is offset relative to the data A1 at different time points through the time sliding window to obtain the offset data , further, the offset data is processed at different offset positions Fit it with the training data A1 to calculate the MSE, where the fitting formula is as follows:

[0079]

[0080] Among them, MSE is the minimum mean square root, Refers to the mth offset data, It refers to the training data corresponding to the offset position of the mth offset data, and N refers to the amount of data involved in fitting.

[0081] Furthermore, through the above fitting formula, the operation timing deviation between the transient operation training data and the transient operation test data can be solved, and then the optimal MSE ( ), and input the optimal MSE into the preset timing lag coefficient calculation formula to calculate the timing lag coefficient of the target heating system, wherein the preset timing lag coefficient calculation formula can be specifically shown as follows:

[0082]

[0083] in, is the timing lag coefficient, T is the preset sampling interval, is the optimal MSE.

[0084] Furthermore, after determining the timing lag coefficient, the timing lag coefficient is used to perform misaligned operation timing calibration on the transient operation training data and the transient operation test data. Specifically, based on the timing lag coefficient, data interpolation is used to adjust the timestamp identifiers of the transient operation training data and the transient operation test data respectively, so that the transient operation training data and the transient operation sequencing data are consistent in timing through a given interpolation method, thereby realizing the operation timing calibration of the transient operation training data and the transient operation test data.

[0085] It can be understood that when the operation timing is aligned by the above method, the detection process of the overall fault detection of the heating system is as follows: 1) obtaining the multi-dimensional historical transient operation data composed of the heating heat exchange station and the steam heat exchange station to be analyzed in the target heating system within a preset time period; 2) according to the operation characteristics (operation timestamp identifier) ​​of the multi-dimensional historical transient operation data, the multi-dimensional historical transient operation data is divided into transient operation training data and transient operation test data, that is, the upstream data and the downstream operation data are obtained by division, so that the above-mentioned preset minimum mean square algorithm is used to align the transient operation training data and the transient operation test data. The transient operation test data is aligned for operation timing, and the transient operation training data and transient operation test data after the operation timing alignment are used together as the transient operation data to be fitted, so as to fit the steady-state relationship later; 3) The multivariate quadratic decoupling fitting method is adopted to fit the transient operation training data and transient operation test data after the operation timing alignment, so as to fit the multidimensional historical steady-state operation data. It can be understood that the fitted multidimensional historical steady-state operation data is used for training the fault detection model and subsequently detecting the fault of the target heating system through the fault detection model; 4) With multi-dimensional historical steady-state operation data, it is possible to reasonably infer the values ​​that the downstream physical quantities will reach after a certain operating sequence when the heating system is online, that is, to use the multi-dimensional historical steady-state operation data at the current time point to predict the multi-dimensional historical steady-state operation data at the next time point; 5) The deviation between the measured values ​​of the downstream physical quantities of the heating system at every moment and the prediction before a certain moment is the difference between the actual measurement and the health benchmark. The greater the difference, the greater the possibility of abnormality in the heating system, and different degrees of early warning are required, that is, the fault detection model can be used to predict the next time point. After obtaining the multi-dimensional historical steady-state operation data, the real-time health of the target heating system is detected through the data difference between the multi-dimensional historical steady-state operation data at the current time point and the multi-dimensional historical steady-state operation data at the next time point. Finally, the fault type of the target heating system is detected based on the real-time health, and different degrees of early warning are made according to the fault type; 6) When the multi-dimensional historical steady-state operation data used for training contains data of a certain fault condition, the corresponding relationship between the upstream and downstream of this section of fault condition data can be matched separately, that is, the fault detection of the target heating system can be completed directly through the fault detection model.

[0086] In this embodiment, the least root mean square method is used to first find the deviation between the upstream and downstream data under various misalignment conditions, so as to accurately determine the operating timing deviation between the transient operation training data and the transient operation test data, and then determine the timing lag coefficient of the target heating system through the operating timing deviation. Finally, the operating timing of the transient operation training data and the transient operation test data is aligned through the timing lag coefficient, and the timing of the transient operation test data can be appropriately advanced. Therefore, it lays a foundation for improving the fitting accuracy of multi-dimensional historical steady-state operation data.

[0087] In one embodiment, a fault detection model of a target heating system is constructed based on multi-dimensional historical steady-state operation data, including:

[0088] Double denoising is performed on the multi-dimensional historical steady-state operation data to obtain the first steady-state operation data and the second steady-state operation data under different denoising dimensions; feature extraction is performed on the first steady-state operation data and the second steady-state operation data respectively to obtain the first steady-state operation characteristics and the second steady-state operation characteristics; and a fault detection model of the target heating system is constructed based on the target steady-state operation characteristics formed by the fusion of the first steady-state operation characteristics and the second steady-state operation characteristics.

[0089] It should be noted that in order to improve the construction accuracy of the fault detection model, before the multi-dimensional historical steady-state operation data is input into the preset fault detection model for feature extraction, the multi-dimensional historical steady-state operation data can be denoised based on the corresponding denoising algorithm, wherein the denoising algorithm may specifically include a flexible morphological filtering optimization algorithm, a wavelet algorithm, an extreme learning machine algorithm, and a particle swarm algorithm, etc. It can be understood that the denoising algorithm is deployed in the filtering unit of the heating system fault detection system, and the filtering unit may be composed of a fixed parameter filtering sub-unit and an optimized filtering sub-unit, and different sub-units are used for denoising processing under different denoising dimensions.

[0090] As an example, preliminary denoising is performed on the first steady-state operation data to obtain the first steady-state operation data under a first preset denoising dimension, and secondary denoising is performed on the first steady-state operation data to obtain the second steady-state operation data under a second preset denoising dimension; feature extraction is performed on the first steady-state operation data to obtain the first steady-state operation feature, and feature extraction is performed on the second steady-state data to obtain the second steady-state operation feature; the first steady-state operation feature and the second steady-state operation feature are concatenated into the target steady-state operation feature, and according to the target steady-state operation feature, a preset fault detection model is iteratively trained, and the trained preset fault detection model is used as the fault detection model of the target heating system.

[0091] As another example, preliminary denoising is performed on the first steady-state operation data to obtain the first steady-state operation data under a first preset denoising dimension, and secondary denoising is performed on the first steady-state operation data to obtain the second steady-state operation data under a second preset denoising dimension; feature extraction is performed on the first steady-state operation data to obtain a first steady-state operation feature, and feature extraction is performed on the second steady-state operation data to obtain a second steady-state operation feature; a first feature weight of the first steady-state operation feature and a second feature weight of the second steady-state operation feature are respectively obtained, and a target steady-state operation feature is obtained by fusing the first steady-state operation feature, the second steady-state operation feature, the first feature weight and the second feature weight.

[0092] Among them, the step of obtaining the target steady-state operation characteristic by fusing the first steady-state operation characteristic, the second steady-state operation characteristic, the first characteristic weight and the second characteristic weight can be performed according to the following formula:

[0093]

[0094] in, is the target steady-state operating characteristic, is the first steady-state operating characteristic, is the first feature weight, is the second steady-state operating characteristic, is the second feature weight, where the sum of the first feature weight and the second feature weight is 1.

[0095] It can be understood that since the first steady-state operation characteristic and the second steady-state operation characteristic are steady-state operation characteristics obtained by denoising the multidimensional historical steady-state operation data under different noise reduction dimensions, although they can reflect the steady-state operation conditions from different spatial scales, the granularity of the second steady-state operation characteristic obtained after multiple noise reductions will be higher than the first steady-state operation characteristic obtained by a single noise reduction. Relatively speaking, the importance of the second steady-state operation characteristic will be higher than the importance of the first steady-state operation characteristic. Therefore, in an implementable manner, the second feature weight can be set to 0.6, and the first feature weight can be set to 0.4.

[0096] It can be understood that the steady-state operation characteristic is a relative concept, which is characterized by the fact that in the steady-state operation state, the operating data maintains a relatively stable state. For example, in the steady-state operation state, the operating data such as pressure, temperature, flow and frequency of the heating system remain relatively stable. At the same time, it is necessary to know that steady-state operation is not a constant state, but a dynamic equilibrium process. The heating system can achieve the transition from the first steady state to the second steady state. For example, when the ambient temperature changes, the heating system will start the adjustment mechanism, which can automatically trigger calibration and feedback to maintain the stability of parameters. Among them, automatic triggering of calibration means that during the steady-state operation, the system will automatically calibrate the system through the automatic calibration mechanism. To maintain the stability of parameters; for example, when the secondary temperature is too high, the system will automatically adjust to reduce the secondary temperature; when the secondary temperature is too low, the system will automatically adjust to increase the secondary temperature. The maintenance of steady state is limited to a certain extent for the heating system, that is, when the environmental changes exceed a certain limit, the steady state may be broken. For example, after the heating system experiences a major accident, the steady state of the heating system will be broken and enter another new steady state. After the first steady-state operation characteristics and the second steady-state operation characteristics are integrated, the effects can be summarized as follows: 1) Dynamic balance and automatic calibration: The target steady-state operation not only maintains dynamic balance, but also has the function of automatic calibration. When the system parameters deviate from the set value, they can be automatically adjusted through the feedback loop to ensure that the system parameters return to the set value; 2) Environmental adaptability: The target steady-state operation characteristics can better adapt to environmental changes. When the external environment changes, the system can maintain the stability of the parameters through the adjustment mechanism to ensure the normal operation of the heating system; 3) Limited capacity: The target steady-state operation characteristics also have limited capacity. When the environmental changes exceed a certain limit, the system may lose its steady state and enter another new steady state. This characteristic enables the heating system to self-adjust and adapt in the face of extreme situations.

[0097] In this embodiment, before constructing a fault detection model of the target heating system based on the multi-dimensional historical steady-state operation data, a filtering unit is deployed in the heating system fault detection system to perform double noise reduction on the multi-dimensional historical steady-state operation data, thereby suppressing and eliminating the interference data in the multi-dimensional historical steady-state operation data, and improving the data signal-to-noise ratio. At the same time, the operating characteristics of the multi-dimensional historical steady-state operation data related to the operating conditions of the target heating system are highlighted, so that the fault detection model obtained by iterative training can accurately identify the operating characteristics of the target heating system, thus laying a foundation for improving the accuracy of heating system fault detection.

[0098] In one embodiment, according to the fault detection model, fault detection is performed on the target heating system, including:

[0099] According to the fault detection model, the real-time health of the target heating system is detected; when it is detected that the real-time health is less than a preset health threshold, the fault type of the target heating system is detected according to the real-time health.

[0100] It should be noted that the deviation between the measured values ​​of the downstream physical quantities of the heating system at every moment and the prediction before a certain moment can be understood as the difference between the actual measurement and the healthy benchmark. The larger the difference value, the greater the possibility of abnormality or failure of the heating system, so that different degrees of warning can be made based on different fault conditions. At the same time, if there is data of a certain fault condition in the training data set used to construct the fault detection model, the correspondence between the upstream and downstream of this section of condition data (operation data) can be fitted separately, and the fitting result can be used for fault detection. That is, when the correspondence between the upstream and downstream at a certain moment is consistent with the correspondence of this fault condition in the historical data, it is determined that this type of fault has occurred at this time. Based on the above, this embodiment can quantify the operation status of the target heating system during the process of fault detection of the target heating system, and accurately identify the fault type of the target heating system when a fault is detected in the target heating system.

[0101] As an example, the real-time operation data of the target heating system is feature extracted according to the fault detection model to obtain real-time operation features, and the real-time health of the target heating system is predicted according to the real-time operation features; it is detected whether the real-time health is less than a preset health threshold, and when it is detected that the real-time health is less than the preset health threshold, the fault type of the target heating system is queried with the real-time health as an index. In this embodiment, the quantitative measurement of the operation status of the target heating system is completed through the fault detection model, and when a fault is detected in the target heating system, the specific fault type of the target heating system is detected based on the mapping relationship between the real-time health and the fault type, thereby improving the detection effect of fault detection on the heating system.

[0102] In one practicable manner, during the process of detecting faults in a heating system, this embodiment first obtains multidimensional historical transient operation data of a target heating system within a preset time period, that is, collects a variety of historical transient operation data for fusion, thereby providing data support for fault detection of the heating system, and then adopts the operation sequence characteristics of the multidimensional historical transient operation data to fit the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data, and combines the artificial intelligence neural network algorithm to construct a fault detection model for detecting the operation status of the target heating system that changes over time, and finally uses the fault detection model to quantitatively detect the fault status of the heating system, and when a fault is detected in the target heating system, detects the specific fault type of the target heating system based on the real-time health status.

[0103] Since the multi-dimensional historical steady-state operation data can reflect the changes in the continuous operation status of the heating system during operation from different dimensions, the fault detection model constructed by the multi-dimensional historical steady-state operation data can accurately detect the operation status of the target heating system that changes over time with the support of data, rather than relying only on human subjective detection when detecting heating system faults. Therefore, it overcomes the technical defects that the fault diagnosis through human qualitative analysis is easily affected by subjective factors and lacks effective data support, resulting in the failure of the obtained fault detection results to reflect the actual operation of the heating system, which makes it easy for the heating system to fail to operate or the heating system to consume a lot of energy. Therefore, the detection accuracy of heating system fault detection is improved.

[0104] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0105] Based on the same inventive concept, the embodiment of the present application also provides a heating system fault detection device for implementing the heating system fault detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more heating system fault detection device embodiments provided below can refer to the limitations of the heating system fault detection method above, and will not be repeated here.

[0106] In an exemplary embodiment, Figure 3 As shown, a heating system fault detection device is provided, comprising: an acquisition module 401, a fitting module 402, a construction module 403 and a detection module 404, wherein:

[0107] An acquisition module 401 is used to acquire multi-dimensional historical transient operation data of a target heating system within a preset time period;

[0108] A determination module 402 is used to fit the multidimensional historical transient operation data according to the operation sequence characteristics of the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing with time;

[0109] A construction module 403 is used to construct a fault detection model of the target heating system according to the multi-dimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes over time;

[0110] The detection module 404 is used to perform fault detection on the target heating system according to the fault detection model.

[0111] In one embodiment, the acquisition module 401 is further used for:

[0112] Acquire multiple historical transient operation data of the target heating system provided by different data sources within the preset time period; fuse each of the transient operation data according to the performance impact weight corresponding to each of the historical transient operation data to obtain the multi-dimensional historical transient operation data.

[0113] In one embodiment, the fitting module 402 is further configured to:

[0114] According to the operation timing characteristics of the multidimensional historical transient operation data, the multidimensional historical transient operation data are divided into transient operation training data and transient operation test data; the operation timing of the transient operation training data and the transient operation test data are aligned, and the transient operation training data and the transient operation test data after the operation timing alignment are used together as a plurality of transient operation data to be fitted; according to the correlation relationship between each of the transient operation data to be fitted, each transient operation data to be fitted is fitted into the multidimensional historical steady-state operation data.

[0115] In one embodiment, the fitting module 402 is further configured to:

[0116] According to the operation timing deviation between the transient operation training data and the transient operation test data, the timing lag coefficient of the target heating system is determined; according to the timing lag coefficient, the operation timing of the transient operation training data and the transient operation test data is aligned.

[0117] In one embodiment, the construction module 403 is further used to:

[0118] Double denoising is performed on the multi-dimensional historical steady-state operation data to obtain first steady-state operation data and second steady-state operation data under different denoising dimensions; feature extraction is performed on the first steady-state operation data and the second steady-state operation data respectively to obtain first steady-state operation characteristics and second steady-state operation characteristics; and a fault detection model of the target heating system is constructed according to the target steady-state operation characteristics formed by the fusion of the first steady-state operation characteristics and the second steady-state operation characteristics.

[0119] In one embodiment, the detection module 404 is further configured to:

[0120] According to the fault detection model, the real-time health of the target heating system is detected; when it is detected that the real-time health is less than a preset health threshold, the fault type of the target heating system is detected according to the real-time health.

[0121] Each module in the above heating system fault detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0122] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for detecting faults in a heating system is implemented. Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0123] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0124] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0125] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0126] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0127] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0128] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting a heating system fault, characterized in that: The method comprises: Obtain multi-dimensional historical transient operation data of the target heating system within a preset time period; According to the operation timing characteristics of the multidimensional historical transient operation data, the multidimensional historical transient operation data is fitted to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing over time; Constructing a fault detection model of the target heating system according to the multi-dimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes over time; According to the fault detection model, fault detection is performed on the target heating system.

2. The method according to claim 1, characterized in that The step of obtaining multi-dimensional historical transient operation data of the target heating system within a preset time period includes: Acquire a plurality of historical transient operation data of the target heating system provided by different data sources within the preset time period; The transient operation data are fused according to the performance impact weights corresponding to the historical transient operation data to obtain the multi-dimensional historical transient operation data.

3. The method according to claim 1, characterized in that The multidimensional historical transient operation data is fitted according to the operation timing characteristics of the multidimensional historical transient operation data to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing over time, including: According to the operation timing characteristics of the multi-dimensional historical transient operation data, the multi-dimensional historical transient operation data is divided into transient operation training data and transient operation test data; Performing operation timing alignment on the transient operation training data and the transient operation test data, and using the transient operation training data and the transient operation test data after the operation timing alignment as a plurality of transient operation data to be fitted; According to the correlation between the transient operation data to be fitted, each transient operation data to be fitted is fitted into the multi-dimensional historical steady-state operation data.

4. The method according to claim 3, characterized in that The performing operation timing alignment on the transient operation training data and the transient operation test data comprises: Determining a timing lag coefficient of the target heating system according to an operation timing deviation between the transient operation training data and the transient operation test data; The transient operation training data and the transient operation test data are aligned in operation timing according to the timing lag coefficient.

5. The method according to claim 1, characterized in that: The method of constructing a fault detection model of the target heating system according to the multi-dimensional historical steady-state operation data comprises: Performing double noise reduction on the multi-dimensional historical steady-state operation data to obtain first steady-state operation data and second steady-state operation data under different noise reduction dimensions; Extracting features from the first steady-state operation data and the second steady-state operation data respectively to obtain a first steady-state operation feature and a second steady-state operation feature; A fault detection model of the target heating system is constructed according to the target steady-state operation characteristics formed by integrating the first steady-state operation characteristics and the second steady-state operation characteristics.

6. The method according to claim 1, characterized in that The step of performing fault detection on the target heating system according to the fault detection model includes: Detecting the real-time health of the target heating system according to the fault detection model; When it is detected that the real-time health status is less than a preset health status threshold, a fault type detection is performed on the target heating system according to the real-time health status.

7. A heating system fault detection device, characterized in that: The device comprises: An acquisition module, used to acquire multi-dimensional historical transient operation data of a target heating system within a preset time period; A fitting module, for fitting the multidimensional historical transient operation data according to the operation timing characteristics of the multidimensional historical transient operation data, to obtain multidimensional historical steady-state operation data reflecting the operation status of the target heating system changing with time; A construction module, used to construct a fault detection model of the target heating system according to the multi-dimensional historical steady-state operation data, wherein the fault detection model is used to detect the operation status of the target heating system that changes over time; A detection module is used to perform fault detection on the target heating system according to the fault detection model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images