Temperature alarm method and device for bus duct, terminal and storage medium

Abstract

The invention provides a temperature alarm method and device for a bus duct, a terminal and a storage medium. The method comprises the following steps: constructing a white box model for representing a corresponding relation between bus current and bus temperature rise according to an equipment mechanism modeling mode and a thermodynamic principle; constructing an initial grey box model between the bus current and the bus temperature rise based on the white box model, and training the initial grey box model based on a machine learning algorithm to obtain a trained target grey box model; predicting a dynamic temperature rise threshold value and a predicted temperature value corresponding to the current current value by using the target grey box model; the current current value is a current value corresponding to a currently monitored actual temperature value of the bus duct, comparing a difference value between the actual temperature value and the predicted temperature value with a dynamic temperature rise threshold to obtain a comparison result, and determining whether to trigger an alarm based on the comparison result. The dynamic threshold value is generated through model prediction, and the problem that the abnormal temperature rise of the bus cannot be accurately fed back due to manual configuration of the static threshold value is solved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a temperature alarm method, device, terminal and storage medium for a bus duct. Background Art

[0002] With the construction of more and more data centers, the safety of the power system needs more reliable protection. The busbar is responsible for the connection between electrical equipment such as transformers at all levels and the corresponding distribution devices in the power system. The function of the busbar is to collect, distribute and transmit electrical energy. As a new type of distribution conductor, the plug-in busbar fully demonstrates its superiority in large current transmission and distribution compared with traditional cables. The application of busbar in high-rise buildings and medium and large data center distribution systems has become quite common.

[0003] At present, in order to ensure the safe operation of the busbar, it is necessary to control the temperature rise within the allowable range. The busbar is in a long-term energized state during operation, which is not conducive to conventional inspection and maintenance. Daily maintenance usually measures the temperature rise of the outer casing and key connections. Moreover, most busbars operate in a relatively humid and dark environment for a long time. The internal insulation material is gradually aged and oxidized, and the bolts at some joints may become loose, which can easily lead to impedance changes and temperature increases at the busbar connections. Once the busbar joint in operation is abnormally overheated, it may cause fire or major safety and quality accidents, causing huge and irreparable casualties and economic property losses to the company.

[0004] However, currently, the bus temperature is monitored in real time and static thresholds are configured based on experience. When the bus temperature exceeds the static threshold, an alarm is generated. However, the static threshold cannot separate the peak and off-peak periods of the business, resulting in the inability to accurately set the static threshold for the alarm. If the static threshold is set too high, the actual abnormal scenario will not be notified to the person in charge during the off-peak period. If the static threshold is set too low, frequent false alarms will occur during the peak period, affecting the judgment of whether the business is healthy. In other words, the accurate setting of the threshold will have a real impact on the business. For a long period of time when the business has just begun to be abnormal, the corresponding alarm event cannot be generated because the threshold is not reached. Since the bus temperature has a certain correlation with the bus current, the static threshold is usually set high, and the alarm generated by the system due to abnormal overheating cannot be accurately judged.

[0005] In summary, the existing bus duct temperature alarm method has the technical problem of being unable to accurately feedback the abnormal temperature rise of the bus due to the manual configuration of the static threshold. Therefore, how to provide a solution to the above technical problem is a problem that technicians in this field need to solve at present. Summary of the invention

[0006] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, a temperature alarm method, device, terminal and storage medium for a bus duct are provided, aiming to solve the problem in the prior art that the abnormal temperature rise of the bus cannot be accurately fed back due to the manual configuration of static thresholds.

[0007] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0008] A temperature alarm method for a bus duct, wherein the method comprises:

[0009] A white box model is constructed based on the equipment mechanism modeling method and thermodynamic principles to characterize the corresponding relationship between bus current and bus temperature rise;

[0010] An initial gray box model between the bus current and the bus temperature rise is constructed based on the white box model, and the initial gray box model is trained based on a machine learning algorithm to obtain a trained target gray box model;

[0011] The target gray box model is used to predict the dynamic temperature rise threshold and the predicted temperature value corresponding to the current current value; wherein the current current value is the current value corresponding to the actual temperature value of the bus duct currently monitored;

[0012] The difference between the actual temperature value and the predicted temperature value is compared with the dynamic temperature rise threshold to obtain a corresponding comparison result, and whether to trigger an alarm is determined based on the comparison result.

[0013] In one implementation, the white box model is:

[0014] ΔT=I 2 Rt / K t ;

[0015] Wherein, ΔT represents the busbar temperature rise, I represents the busbar current, R represents the resistance of the conductor, K t represents the total heat dissipation coefficient, and t represents time.

[0016] In one implementation, the constructing an initial gray box model between the bus current and the bus temperature rise based on the white box model includes:

[0017] Determine the physical characteristics of the equipment of the white box model, and perform mathematical abstraction processing on the physical characteristics of the equipment of the white box model to determine the gray box model target, input features and basic model of the bus duct;

[0018] Constructing an initial gray box model between the bus current and the bus temperature rise based on the gray box model target, the input characteristics and the basic model;

[0019] The target of the gray box model is the bus temperature rise, the input feature is the bus current, and the basic model is a quadratic function containing a random quantity.

[0020] In one implementation, the initial grey box model is:

[0021] ΔT=a1x+a2x 2 +ε;

[0022] Wherein, ΔT represents the bus temperature rise, a1 represents the first coefficient, a2 represents the second coefficient, x represents the bus current, and ε represents the random quantity.

[0023] In one implementation, the training of the initial gray box model based on a machine learning algorithm to obtain a trained target gray box model includes:

[0024] Based on the linear regression algorithm in the machine learning algorithm, the initial grey box model is trained using pre-collected training data to obtain a trained target grey box model.

[0025] In one implementation, after the initial gray box model is trained based on a machine learning algorithm to obtain a trained target gray box model, the method further includes:

[0026] Using the pre-collected verification data set to verify the target gray box model to obtain a corresponding verification result;

[0027] Based on the verification result, it is determined whether to continue to perform the step of training the initial gray box model based on the machine learning algorithm to obtain a trained target gray box model.

[0028] In one implementation, after the initial gray box model is trained based on a machine learning algorithm to obtain a trained target gray box model, the method further includes:

[0029] Performing reinforcement learning on the target gray box model to obtain an enhanced target gray box model;

[0030] The method of using the target gray box model to predict a dynamic temperature rise threshold and a predicted temperature value corresponding to the current current value includes:

[0031] The enhanced target gray box model is used to predict the dynamic temperature rise threshold and the predicted temperature value corresponding to the current current value.

[0032] The present invention also discloses a temperature alarm device for a bus duct, wherein the device comprises:

[0033] The first model building module is used to build a white box model for characterizing the corresponding relationship between bus current and bus temperature rise according to the equipment mechanism modeling method and thermodynamic principles;

[0034] A second model building module, used for building an initial grey box model between the bus current and the bus temperature rise based on the white box model;

[0035] A model training module, used to train the initial gray box model based on a machine learning algorithm to obtain a trained target gray box model;

[0036] A prediction module, used to predict the dynamic temperature rise threshold and predicted temperature value corresponding to the current current value by using the target gray box model; wherein the current current value is the current value corresponding to the actual temperature value of the bus duct currently monitored;

[0037] The alarm module is used to compare the difference between the actual temperature value and the predicted temperature value with the dynamic temperature rise threshold to obtain a corresponding comparison result, and determine whether to trigger an alarm based on the comparison result.

[0038] The present invention also discloses a terminal, which includes: a memory, a processor, and a temperature alarm program for the bus duct stored in the memory and executable on the processor. When the temperature alarm program for the bus duct is executed by the processor, the steps of the temperature alarm method for the bus duct as described above are implemented.

[0039] The present invention also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program can be executed to implement the steps of the temperature alarm method for the bus duct as described above.

[0040] The present invention provides a temperature alarm method, device, terminal and storage medium for a bus duct, wherein the temperature alarm method for the bus duct comprises: constructing a white box model for characterizing the corresponding relationship between the bus current and the bus temperature rise according to the equipment mechanism modeling method and the thermodynamic principle; constructing an initial gray box model between the bus current and the bus temperature rise based on the white box model, and training the initial gray box model based on a machine learning algorithm to obtain a trained target gray box model; using the target gray box model to predict a dynamic temperature rise threshold and a predicted temperature value corresponding to a current current value; wherein the current current value is a current value corresponding to an actual temperature value of the bus duct currently monitored; comparing the difference between the actual temperature value and the predicted temperature value with the dynamic temperature rise threshold to obtain a corresponding comparison result, and determining whether to trigger an alarm based on the comparison result. The present invention models the bus duct, constructs a white-box model between bus temperature and bus current according to the equipment mechanism modeling method and thermodynamic principles, and then constructs a corresponding gray-box model based on the white-box model, and trains the gray-box model based on a machine learning algorithm to fit a real model, thereby improving the adaptability of the model. That is, the modeling of the bus duct equipment is achieved by combining the equipment mechanism with big data machine learning, so that the alarm has wider applicability and better effect. Finally, a dynamic threshold is generated through model prediction, and the dynamic threshold can automatically adapt to temperature anomalies under different currents, thereby solving the problem of inability to accurately feedback abnormal temperature rise of the bus due to manually configured static thresholds. That is, the technical solution of the present application enables the alarm strategy to follow the thermodynamic principles, break away from pure data dependence, and avoid anti-logic, thereby having higher reliability and better alarm effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of a preferred embodiment of the temperature alarm method of the bus duct in the present invention;

[0042] Figure 2 It is a schematic diagram of the relationship between the temperature rise and the current load of the bus duct in the present invention;

[0043] Figure 3 It is a schematic diagram of the relationship between the temperature and current of the bus duct in the present invention;

[0044] Figure 4 It is a functional principle block diagram of a preferred embodiment of the temperature alarm device for bus duct in the present invention;

[0045] Figure 5 It is a functional principle block diagram of a preferred embodiment of the terminal in the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of the temperature alarm method for the bus duct in the present invention. Figure 1 As shown, the temperature alarm method of the bus duct according to the embodiment of the present invention includes:

[0048] Step S100: construct a white box model for characterizing the corresponding relationship between bus current and bus temperature rise according to the equipment mechanism modeling method and thermodynamic principles.

[0049] In the embodiment of the present application, the physical characteristics of the bus duct equipment are analyzed according to the equipment mechanism modeling method and thermodynamic principles, and then a white box model is constructed to characterize the corresponding relationship between the bus current and the bus temperature rise, that is, a thermodynamic white box power model between the current and the temperature rise is constructed for the bus duct equipment.

[0050] Specifically, the white box model may be:

[0051] ΔT=I 2 Rt / K t ;

[0052] Wherein, ΔT represents the busbar temperature rise, I represents the busbar current, R represents the resistance of the conductor, K t represents the total heat dissipation coefficient, and t represents time.

[0053] It should be pointed out that the busbar temperature rise is the temperature rise caused by the heat generated by the current passing through the conductor. In this process, the existence of conductor resistance is involved. The resistance will generate energy loss when the current passes through the conductor and release it in the form of heat, thereby increasing the conductor temperature. The busbar temperature rise calculation formula in the embodiment of the present application is only an approximation and is actually affected by other factors, such as ambient temperature, cooling method, and wiring method.

[0054] It can be understood that the white box model can characterize the quadratic relationship between the bus temperature rise and the bus current, where the load curve of temperature rise and current can be found in Figure 2 shown.

[0055] like Figure 1 As shown, the temperature alarm method for the bus duct described in this embodiment also includes:

[0056] Step S200: construct an initial gray box model between the bus current and the bus temperature rise based on the white box model, and train the initial gray box model based on a machine learning algorithm to obtain a trained target gray box model.

[0057] In one embodiment of the present application, step S200 specifically includes:

[0058] Step S210: determining the physical characteristics of the device of the white box model, and performing mathematical abstraction processing on the physical characteristics of the device of the white box model to determine the gray box model target, input features and basic model of the bus duct;

[0059] Step S220, constructing an initial gray box model between the bus current and the bus temperature rise based on the gray box model target, the input feature and the basic model; wherein the gray box model target is the bus temperature rise, the input feature is the bus current, and the basic model is a univariate quadratic function containing a random quantity.

[0060] It can be understood that the construction of the gray box model between the bus temperature rise and the bus current is mainly through mathematical abstraction of the physical characteristics of the equipment on the white box model, so that the gray box model target of the bus duct equipment can be clarified, that is, the model target, input features and optional basic models, that is, basic mathematical functions, and the loss function used in the subsequent training of the initial gray box model can also be clarified at the same time, as shown in Table 1:

[0061] Table 1

[0062] Model Objective Busbar temperature rise ΔT Input Features Bus current Available basic models The quadratic function to be corrected, including random quantities Loss Function The squared difference between the true value and the predicted value (i.e. L2 loss)

[0063] Specifically, the initial gray box model is:

[0064] ΔT=a1x+a2x 2 +ε;

[0065] Wherein, ΔT represents the bus temperature rise, a1 represents the first coefficient, a2 represents the second coefficient, x represents the bus current, and ε represents the random quantity.

[0066] The embodiment of the present application constructs a corresponding gray box model based on the white box model, and trains the gray box model based on the machine learning algorithm to fit the real model, thereby improving the adaptability of the model, that is, the modeling of the bus duct equipment is achieved by combining the equipment mechanism with big data machine learning, so that the alarm is more widely applicable and more effective, and the calculation efficiency is faster when the alarm is generated. It should be noted that this modeling method combining the equipment mechanism with big data machine learning is not only applicable to the bus duct equipment of the present application, but can also be used for the modeling of switch cabinet circuit breakers.

[0067] Specifically, training the initial gray box model based on a machine learning algorithm to obtain a trained target gray box model may specifically include: training the initial gray box model based on a linear regression algorithm in the machine learning algorithm and using pre-collected training data to obtain a trained target gray box model.

[0068] For example, relevant historical data is collected, and then the initial gray box model is trained using the gradient descent method and these historical data. The loss function used by the gradient descent method describes the error between the predicted value and the true value, so the loss function corresponding to the optimal solution of parameter a should be the minimum value.

[0069] The known loss function is:

[0070] cost = (Preal - Ppred) 2 ;

[0071] The predicted values ​​are:

[0072] Ppred=a1x 1 +a2x 2 +Random amount;

[0073] Therefore, the loss function can be:

[0074] cost=(Preal-(a1x 1 +a2x 2 +Random amount)) 2 ;

[0075] Therefore, the gradient descent method can be used to solve the corresponding a value when the cost takes the minimum value, so as to complete the training of the initial gray box model between the bus temperature rise and the bus current and obtain the target gray box model.

[0076] It is understandable that the embodiment of the present application repeatedly iterates the machine learning model through the loss function, and adopts the gradient descent method in the iterative process to find the optimal solution, among which linear regression is a common type in machine learning.

[0077] Through the above model construction method, the target gray box model corresponding to all buses in the current scene can be constructed.

[0078] In this embodiment, after the initial gray box model is trained based on the machine learning algorithm to obtain a trained target gray box model, the method may further include: using a pre-collected verification data set to verify the target gray box model to obtain a corresponding verification result; and determining whether to continue to perform the step of training the initial gray box model based on the machine learning algorithm to obtain a trained target gray box model based on the verification result. It is understandable that the relationship between the bus temperature rise and the bus current is modeled, and then the machine learning algorithm is selected to train the model, and the trained model is further verified to ensure the accuracy and reliability of the model.

[0079] like Figure 1 As shown, the temperature alarm method for the bus duct described in this embodiment also includes:

[0080] Step S300: using the target gray box model to predict a dynamic temperature rise threshold and a predicted temperature value corresponding to a current current value; wherein the current current value is a current value corresponding to an actual temperature value of the bus duct currently monitored.

[0081] It is understandable that the actual temperature value of the bus duct is monitored in real time, where the temperature of each monitoring point on the same circuit should not be much different because of the same current, and the corresponding bus current value under the actual temperature value is determined at the same time, and then based on the constructed target gray box model between the bus temperature rise and the bus current, the reasonable range of temperature rise can be calculated, that is, the predicted temperature rise threshold, and the predicted temperature value corresponding to the current current value of the bus duct can also be predicted at the same time. The dynamic threshold based on the algorithm does not require engineers to configure each monitoring point, prevent mismatching and missing matching, and simplify the configuration process. Moreover, compared with the manually configured static threshold, the dynamic threshold predicted based on the mechanism model and the big data machine learning algorithm can automatically adapt to the temperature abnormality values ​​under different currents, that is, the dynamic threshold has a wider adaptability.

[0082] It should be pointed out that in order to increase the adaptability to the environment, the model needs to be operated periodically. The latest historical data can be used for reinforcement learning, that is, the target gray box model is reinforced to obtain an enhanced target gray box model. The enhanced target gray box model is then used to predict the dynamic temperature rise threshold and predicted temperature value corresponding to the current current value.

[0083] like Figure 1 As shown, the temperature alarm method for the bus duct described in this embodiment also includes:

[0084] Step S400: Compare the difference between the actual temperature value and the predicted temperature value with the dynamic temperature rise threshold to obtain a corresponding comparison result, and determine whether to trigger an alarm based on the comparison result.

[0085] It can be understood that the difference between the actual temperature value corresponding to the current current value of the bus duct and the predicted temperature is determined, and then the difference is compared with the dynamic temperature rise threshold predicted by the model. If the difference is greater than the dynamic temperature rise threshold predicted by the model, an alarm is triggered; if the difference is not greater than the dynamic temperature rise threshold predicted by the model, no alarm is triggered.

[0086] For example, see Figure 3 As shown, when the current current value is 0.8A, the predicted temperature value of the bus duct predicted by the model is 2.5 degrees Celsius, and the actual temperature value at the current current value is 4 degrees Celsius. It can be seen that the actual temperature value deviates from the predicted temperature value, and the degree of deviation is greater than the reasonable range value of the predicted temperature rise (+ΔT=10%), then an alarm is triggered. In other words, the temperature change deviates from the curve of temperature and load current fitting, especially when it is positively deviated and exceeds the reasonable range value of temperature rise, an alarm is triggered.

[0087] In one embodiment, if Figure 4 As shown, based on the above-mentioned bus duct temperature alarm method, the present invention also provides a bus duct temperature alarm device, including:

[0088] The first model building module 100 is used to build a white box model for characterizing the corresponding relationship between bus current and bus temperature rise according to the equipment mechanism modeling method and thermodynamic principles;

[0089] A second model building module 200, configured to build an initial grey box model between the bus current and the bus temperature rise based on the white box model;

[0090] A model training module 300 is used to train the initial grey box model based on a machine learning algorithm to obtain a trained target grey box model;

[0091] The prediction module 400 is used to predict the dynamic temperature rise threshold and the predicted temperature value corresponding to the current current value by using the target gray box model; wherein the current current value is the current value corresponding to the actual temperature value of the bus duct currently monitored;

[0092] The alarm module 500 is used to compare the difference between the actual temperature value and the predicted temperature value with the dynamic temperature rise threshold to obtain a corresponding comparison result, and determine whether to trigger an alarm based on the comparison result.

[0093] Figure 5 A schematic diagram of the structure of a terminal provided in an embodiment of the present application. The terminal may include:

[0094] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0095] When the processor 502 executes the program, the temperature alarm method for the bus duct provided in the above embodiment is implemented.

[0096] Furthermore, the terminal further includes:

[0097] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0098] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0099] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0100] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0101] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0102] The processor 502 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0103] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the temperature alarm method of the bus duct as described above is implemented.

[0104] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0105] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0106] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes additional implementations, in which the order shown or discussed may not be followed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can read instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary and then storing it in a computer memory.

[0108] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0109] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0110] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0111] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

[0112] In summary, the present invention discloses a temperature alarm method, device, terminal and storage medium for a bus duct, and the temperature alarm method for the bus duct includes: constructing a white box model for characterizing the correspondence between the bus current and the bus temperature rise according to the equipment mechanism modeling method and the thermodynamic principle; constructing an initial gray box model between the bus current and the bus temperature rise based on the white box model, and training the initial gray box model based on a machine learning algorithm to obtain a trained target gray box model; using the target gray box model to predict a dynamic temperature rise threshold and a predicted temperature value corresponding to a current current value; wherein the current current value is a current value corresponding to the actual temperature value of the bus duct currently monitored; comparing the difference between the actual temperature value and the predicted temperature value with the dynamic temperature rise threshold to obtain a corresponding comparison result, and determining whether to trigger an alarm based on the comparison result. The present invention models the bus duct, constructs a white-box model between bus temperature and bus current according to the equipment mechanism modeling method and thermodynamic principles, and then constructs a corresponding gray-box model based on the white-box model, and trains the gray-box model based on a machine learning algorithm to fit a real model, thereby improving the adaptability of the model. That is, the modeling of the bus duct equipment is achieved by combining the equipment mechanism with big data machine learning, so that the alarm has wider applicability and better effect. Finally, a dynamic threshold is generated through model prediction, and the dynamic threshold can automatically adapt to temperature anomalies under different currents, thereby solving the problem of inability to accurately feedback abnormal temperature rise of the bus due to manually configured static thresholds. That is, the technical solution of the present application enables the alarm strategy to follow the thermodynamic principles, break away from pure data dependence, and avoid anti-logic, thereby having higher reliability and better alarm effect.

[0113] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A temperature alarm method for a bus duct, characterized in that: The method comprises: A white box model is constructed based on the equipment mechanism modeling method and thermodynamic principles to characterize the corresponding relationship between bus current and bus temperature rise; An initial gray box model between the bus current and the bus temperature rise is constructed based on the white box model, and the initial gray box model is trained based on a machine learning algorithm to obtain a trained target gray box model; The target gray box model is used to predict the dynamic temperature rise threshold and the predicted temperature value corresponding to the current current value; wherein the current current value is the current value corresponding to the actual temperature value of the bus duct currently monitored; The difference between the actual temperature value and the predicted temperature value is compared with the dynamic temperature rise threshold to obtain a corresponding comparison result, and whether to trigger an alarm is determined based on the comparison result.

2. The temperature alarm method of bus duct according to claim 1 is characterized in that: The white box model is: ΔT=I 2 Rt / K t ; Wherein, ΔT represents the busbar temperature rise, I represents the busbar current, R represents the resistance of the conductor, K t represents the total heat dissipation coefficient, and t represents time.

3. The temperature alarm method for bus duct according to claim 1 is characterized in that: The constructing an initial gray box model between the bus current and the bus temperature rise based on the white box model includes: Determine the physical characteristics of the equipment of the white box model, and perform mathematical abstraction processing on the physical characteristics of the equipment of the white box model to determine the gray box model target, input features and basic model of the bus duct; Constructing an initial gray box model between the bus current and the bus temperature rise based on the gray box model target, the input characteristics and the basic model; The target of the gray box model is the bus temperature rise, the input feature is the bus current, and the basic model is a quadratic function containing a random quantity.

4. The temperature alarm method for bus duct according to claim 3 is characterized in that: The initial grey box model is: ΔT=a1x+a2x 2 +e; Wherein, ΔT represents the bus temperature rise, a1 represents the first coefficient, a2 represents the second coefficient, x represents the bus current, and ε represents the random quantity.

5. The temperature alarm method for bus duct according to claim 1, characterized in that: The step of training the initial gray box model based on a machine learning algorithm to obtain a trained target gray box model includes: Based on the linear regression algorithm in the machine learning algorithm, the initial grey box model is trained using pre-collected training data to obtain a trained target grey box model.

6. The temperature alarm method for bus duct according to claim 1, characterized in that: After the initial grey box model is trained based on the machine learning algorithm to obtain a trained target grey box model, the method further includes: Using the pre-collected verification data set to verify the target gray box model to obtain a corresponding verification result; Based on the verification result, it is determined whether to continue to perform the step of training the initial gray box model based on the machine learning algorithm to obtain a trained target gray box model.

7. The temperature alarm method for bus duct according to any one of claims 1 to 6, characterized in that: After the initial grey box model is trained based on the machine learning algorithm to obtain a trained target grey box model, the method further includes: Performing reinforcement learning on the target gray box model to obtain an enhanced target gray box model; The method of using the target gray box model to predict a dynamic temperature rise threshold and a predicted temperature value corresponding to the current current value includes: The enhanced target gray box model is used to predict the dynamic temperature rise threshold and the predicted temperature value corresponding to the current current value.

8. A temperature alarm device for a bus duct, characterized in that: The device comprises: The first model building module is used to build a white box model for characterizing the corresponding relationship between bus current and bus temperature rise according to the equipment mechanism modeling method and thermodynamic principles; A second model building module, used for building an initial grey box model between the bus current and the bus temperature rise based on the white box model; A model training module, used to train the initial gray box model based on a machine learning algorithm to obtain a trained target gray box model; A prediction module, used to predict the dynamic temperature rise threshold and predicted temperature value corresponding to the current current value by using the target gray box model; wherein the current current value is the current value corresponding to the actual temperature value of the bus duct currently monitored; The alarm module is used to compare the difference between the actual temperature value and the predicted temperature value with the dynamic temperature rise threshold to obtain a corresponding comparison result, and determine whether to trigger an alarm based on the comparison result.

9. A terminal, characterized in that: include: A memory, a processor, and a temperature alarm program for a bus duct stored in the memory and executable on the processor, wherein the temperature alarm program for the bus duct, when executed by the processor, implements the steps of the temperature alarm method for the bus duct as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program can be executed to implement the steps of the bus duct temperature alarm method according to any one of claims 1 to 7.

Images