Method and apparatus for training a model for predicting temperature rise of a heat generating element in a switching device

Abstract

Embodiments of the present disclosure provide a method and apparatus for training a model for predicting temperature rise of a heating element in a switchgear. The method comprises obtaining a model for the prediction of the temperature rise, the model comprising a plurality of inputs, outputs and a plurality of parameters to be determined; obtaining n+1 sets of physical quantities related to the heating element, each set of physical quantities being collected at a corresponding one of n+1 time points under a normal operating state of the heating element, the n+1 time points being spaced apart from each other by a time step, each set of physical quantities comprising a current and an actual temperature of the heating element and an ambient temperature; converting the actual temperature in each set of physical quantities into an actual temperature rise based on the corresponding ambient temperature; and training the model with the current, the actual temperature rise and the ambient temperature to determine the plurality of parameters.

Description

Technical Field

[0001] The exemplary embodiments of this disclosure generally relate to the field of switching devices, and more specifically, to methods and apparatus for training models for predicting temperature rise of heating elements in switching devices, methods and apparatus for determining temperature rise of heating elements in switching devices, computer-readable storage media, and computer program products. Background Technology

[0002] Switchgear is electrical equipment in a power system that performs opening / closing, control, or protection functions during power generation, transmission, distribution, and power conversion. As switchgear is used over time, the conductive connections (such as contacts) in the main circuit may experience increased resistance due to mechanical vibration, wear, and manufacturing defects, leading to contact temperature rise or even contact burnout. This can result in safety accidents. Furthermore, improper on-site installation of switchgear and component damage are also major factors contributing to abnormal temperature rises in switchgear.

[0003] The conventional method for detecting such abnormal temperature rises is to use a portable infrared device to detect the temperature of the contacts in the switchgear through an observation window. The detected temperature is then compared to the temperature limit of the contacts under rated current to determine if an abnormal temperature rise exists in the switchgear contacts. However, this detection method is not always accurate and is inefficient. Recently, online temperature monitoring systems have been applied to switchgear. However, these online temperature monitoring systems mainly focus on temperature acquisition and do not effectively detect abnormal temperature rises.

[0004] Therefore, an improved solution for monitoring temperature rise in switching equipment is needed. Summary of the Invention

[0005] In view of the aforementioned problems, exemplary embodiments of this disclosure propose a real-time regression model for predicting the temperature rise of heating elements in switching equipment and a method for detecting abnormal temperature rises in switching equipment. The embodiments of this disclosure are applicable to different operating conditions and settings of switching equipment. The embodiments of this disclosure can reduce the power outage time of switching equipment and improve the reliability of switching equipment.

[0006] In a first aspect, an example embodiment of this disclosure provides a method for training a model for predicting the temperature rise of a heating element in a switching device. The method includes: acquiring a model for predicting the temperature rise, the model including multiple inputs, outputs, and multiple parameters to be determined; acquiring n+1 sets of physical quantities related to the heating element, each set of physical quantities being collected at a corresponding time point among n+1 time points under normal operating conditions of the heating element, the n+1 time points being spaced apart by a time step, each set of physical quantities including the current and actual temperature of the heating element and the ambient temperature; converting the actual temperature in each set of physical quantities into an actual temperature rise based on the corresponding ambient temperature; and training the model using the current, the actual temperature rise, and the ambient temperature to determine the multiple parameters.

[0007] The proposed model is a modified transient thermal balance equation with undetermined thermal and energy parameters. Both the time constant and the dynamic current load are considered as functions of temperature rise when building the model. The model trained according to the method of the first aspect can be used to predict transient or steady-state temperature rise under any current load. This model is designed with strong physical constraints and few parameters, preventing overfitting on most switching equipment operating loads. Through these embodiments, the downtime of switching equipment can be reduced and the reliability of switching equipment can be improved.

[0008] In some embodiments, training the model with current, actual temperature rise, and ambient temperature includes: for each time step, creating n equations by using the current, actual temperature rise, and ambient temperature corresponding to the start time of the time step as inputs to the model and using the actual temperature rise corresponding to the end time of the time step as the output of the model, and solving the n equations to determine multiple parameters. Through this embodiment, by inserting n+1 sets of physical quantities into the model, n equations can be obtained and solved to determine multiple parameters.

[0009] In some embodiments, each of the n equations is created using a discrete approximation scheme or the Runge-Kutta iterative method. Through such embodiments, the n equations can be reliably obtained using either a discrete approximation scheme or the Runge-Kutta iterative method.

[0010] In some embodiments, n equations are solved using the least squares method. Through these embodiments, n equations can be solved using the least squares method to determine multiple parameters.

[0011] In some embodiments, the heating element includes at least one of a busbar contact, an upper circuit breaker contact finger, a lower circuit breaker contact finger, and a cable contact. In such embodiments, the temperature rise of these contacts can be reliably predicted using a trained model.

[0012] In a second aspect, exemplary embodiments of this disclosure provide a method for determining the temperature rise of a heating element in a switching device, the method comprising: predicting the temperature rise of the heating element in the switching device using a model trained according to the method of the first aspect. Through these embodiments, the temperature rise of the heating element in the switching device can be reliably predicted using the trained model.

[0013] In some embodiments, predicting the temperature rise of a heating element using a model includes: acquiring the real-time current of the heating element and the ambient temperature collected in a first time step; and predicting the temperature rise of the heating element in the first time step by inputting the real-time current, the ambient temperature, and the predicted temperature rise in a second time step prior to the first time step into the model. Through such embodiments, the temperature rise in a current time step can be reliably predicted using the current, the ambient temperature, and the predicted temperature rise in previous time steps.

[0014] In some embodiments, the method further includes: acquiring the real-time temperature of the heating element collected in a first time step; converting the real-time temperature of the heating element into a real-time temperature rise based on the ambient temperature; and triggering an alarm in response to the difference between the real-time temperature rise and the predicted temperature rise exceeding a predetermined threshold. Through such embodiments, abnormal temperature rises in switching equipment can be detected in a timely manner, thereby enabling corresponding maintenance to be performed on the switching equipment.

[0015] In some embodiments, predicting the temperature rise of a heating element includes predicting at least one of a transient temperature rise or a steady-state temperature rise. These embodiments enable the prediction of either a transient or steady-state temperature rise of a heating element under any current load.

[0016] In a third aspect, an exemplary embodiment of this disclosure provides an apparatus for training a model for predicting the temperature rise of a heating element in a switching device. The apparatus includes: at least one processor; and at least one memory including instructions stored thereon, which, when executed by the at least one processor, cause the at least one processor to perform the following actions: acquiring a model for predicting the temperature rise, the model including a plurality of inputs, outputs, and a plurality of parameters to be determined; acquiring n+1 sets of physical quantities associated with the heating element, each set of physical quantities being collected at a corresponding time point among n+1 time points under normal operating conditions of the heating element, the n+1 time points being spaced apart by a time step, each set of physical quantities including the current and actual temperature of the heating element and the ambient temperature; converting the actual temperature in each set of physical quantities into an actual temperature rise based on the corresponding ambient temperature; and training the model using the current, the actual temperature rise, and the ambient temperature to determine the plurality of parameters.

[0017] In some embodiments, training the model with current, actual temperature rise, and ambient temperature includes: for each time step, creating equations to obtain n equations by using the current, actual temperature rise, and ambient temperature corresponding to the start time of the time step as inputs to the model and using the actual temperature rise corresponding to the end time of the time step as the output of the model; and solving the n equations to determine multiple parameters.

[0018] In some embodiments, each of the n equations is created using a discrete approximation scheme or the Runge-Kutta iterative method.

[0019] In some embodiments, the n equations are solved using the least squares method.

[0020] In some embodiments, the heating element includes at least one of the following: busbar contact, circuit breaker upper contact finger, circuit breaker lower contact finger, and cable contact.

[0021] In a fourth aspect, an exemplary embodiment of the present disclosure provides an apparatus for determining the temperature rise of a heating element in a switching device, the apparatus comprising: at least one processor; and at least one memory including instructions stored thereon, which, when executed by the at least one processor, cause the at least one processor to perform the following actions, including: predicting the temperature rise of the heating element in the switching device using a model trained by using the apparatus according to the third aspect.

[0022] In some embodiments, predicting the temperature rise of a heating element using a model includes: acquiring the real-time current of the heating element and the ambient temperature collected in a first time step; and predicting the temperature rise of the heating element in the first time step by inputting the real-time current, the ambient temperature, and the predicted temperature rise in a second time step prior to the first time step into the model.

[0023] In some embodiments, the action further includes: acquiring the real-time temperature of the heating element collected in a first time step; converting the real-time temperature of the heating element into a real-time temperature rise based on the ambient temperature; and triggering an alarm in response to the difference between the real-time temperature rise and the predicted temperature rise exceeding a predetermined threshold.

[0024] In some embodiments, predicting the temperature rise of the heating element includes predicting at least one of the transient temperature rise or the steady-state temperature rise of the heating element.

[0025] In some embodiments, at least one processor includes at least one of a local processor or a remote processor.

[0026] In some embodiments, the remote processor includes a cloud computing node.

[0027] In a fifth aspect, exemplary embodiments of the present disclosure provide a computer-readable storage medium having instructions stored thereon that, when executed by at least one processor, cause the at least one processor to perform the method according to the first and second aspects.

[0028] In a sixth aspect, exemplary embodiments of the present disclosure provide a computer program product including instructions that, when executed by at least one processor, cause the at least one processor to perform the method according to the first and second aspects. Attached Figure Description

[0029] The accompanying drawings described herein are provided to further explain this disclosure and constitute a part of this disclosure. The exemplary embodiments of this disclosure and their explanations are intended to explain this disclosure and not to unduly limit it.

[0030] Figure 1 A schematic diagram of a switching device according to an embodiment of the present disclosure is shown;

[0031] Figure 2 The illustration shows a flowchart of a method for training a model for predicting the temperature rise of a heating element in a switching device, according to an embodiment of the present disclosure.

[0032] Figure 3 The illustration shows a flowchart of training a model using current, actual temperature rise, and ambient temperature according to an embodiment of the present disclosure.

[0033] Figure 4 The illustration shows a flowchart of a method for determining the temperature rise of a heating element in a switching device according to an embodiment of the present disclosure;

[0034] Figure 5 The illustration shows a flowchart of predicting the temperature rise of a heating element using a model according to an embodiment of the present disclosure;

[0035] Figure 6 An example test arrangement of a switching device according to an embodiment of the present disclosure is illustrated;

[0036] Figures 7 to 8 The diagram shows... Figure 6 The predicted temperature rise of the heating element in the example test equipment; and

[0037] Figure 9 The illustration shows a schematic diagram of an apparatus for training a model for predicting and / or determining temperature rise according to an embodiment of the present disclosure.

[0038] In all the accompanying drawings, the same or similar reference numerals are used to indicate the same or similar elements. Detailed Implementation

[0039] The principles of this disclosure will now be described with reference to several exemplary embodiments illustrated in the accompanying drawings. Although exemplary embodiments of this disclosure are illustrated in the drawings, it should be understood that these embodiments are described only to enable those skilled in the art to better understand and implement this disclosure, and not to limit the scope of this disclosure in any way.

[0040] The terms “comprising” or “including” and variations thereof shall be understood as open-ended terms meaning “including but not limited to”. Unless the context clearly indicates otherwise, the term “or” shall be understood as “and / or”. The term “based on” shall be understood as “at least partially based on”. The term “operably” means a function, action, movement, or state that can be realized by operation caused by a user or external mechanism. The terms “one embodiment” and “embodiment” shall be understood as “at least one embodiment”. The term “another embodiment” shall be understood as “at least one other embodiment”. The terms “first,” “second,” etc., may refer to different or the same objects. Other explicit and implicit definitions may be included below. Unless the context clearly indicates otherwise, the definitions of terms are consistent throughout the specification.

[0041] As discussed above, conventional methods for detecting abnormal temperature rises are not always accurate and are inefficient, and conventional online temperature monitoring systems mainly focus on temperature acquisition rather than efficient abnormal temperature rise detection. According to embodiments of this disclosure, a real-time regression model for predicting the temperature rise of heating elements in switching equipment and a method for detecting abnormal temperature rises in switching equipment are proposed; the time regression model and the abnormal temperature rise detection method are adaptable to different operating conditions and settings of the switching equipment. As will be described in detail in the following paragraphs, the above ideas can be implemented in various ways.

[0042] In the following text, reference will be made to Figures 1 to 9 The principles of this disclosure are described in detail.

[0043] First refer to Figure 1 , Figure 1 A schematic diagram of a switching device 100 according to an embodiment of the present disclosure is shown. Figure 1 As shown, the switchgear 100 generally includes bus contacts 101, upper circuit breaker contacts 102, lower circuit breaker contacts 103, and cable contacts 104. During operation of the switchgear 100, the temperatures of the bus contacts 101, upper circuit breaker contacts 102, lower circuit breaker contacts 103, and cable contacts 104 may rise, which may adversely affect the normal function of the switchgear 100. In the context of this disclosure, each of the bus contacts 101, upper circuit breaker contacts 102, lower circuit breaker contacts 103, and cable contacts 104 may be referred to as a heating element of the switchgear 100. It should be understood that this disclosure focuses on the prediction of temperature rise of the heating elements, and therefore detailed descriptions of other structures or operations of the switchgear 100 are omitted.

[0044] To predict the temperature rise of the heating element in the switching device 100, embodiments of this disclosure propose model assumptions. Since a portion of the heat generated by the heating element during operation of the switching device 100 is dissipated and another portion is absorbed by the heating element, it is assumed that the heating element in the switching device 100 satisfies the heat balance equation expressed by equation (1) during this period:

[0045] pdt = K T Aτdt+cmdτ (1),

[0046] pdt represents the total heat generated by the heating elements in the switching equipment during dt;

[0047] K T Aτdt represents the heat dissipated by the heating element during the period dt;

[0048] cmdτ represents the amount of heat absorbed by the heating element when its temperature rises by dτ during the period dt.

[0049] p represents the total heating power of the heating element;

[0050] K T Indicates the heat dissipation coefficient of the heat-generating element;

[0051] A represents the effective heat dissipation area of ​​the heating element;

[0052] τ represents the temperature rise of the heating element;

[0053] c represents the specific heat of the heating element;

[0054] m represents the mass of the heating element.

[0055] In engineering, heat dissipation takes the forms of heat conduction, heat convection, and heat radiation. For simplicity, these three heat dissipation methods are combined, namely K. T Aτ is used to represent the overall heat dissipation process. K T The choice between A and K usually depends on the specific application scenario. This is based on K derived from similar theories. T Expression Simplification K T Thus, equation (2) is obtained:

[0056]

[0057] λ and γ are undetermined parameters.

[0058] To solve equation (1), two example methods are provided in this disclosure.

[0059] Method I

[0060] Assume that at t = t0, under the initial condition τ = τ0, the integral calculation of equation (1) is performed over a short time interval from t0 to t1. Since the time interval from t0 to t1 is very short, the temperature rise of the heating element is small. Therefore, the heat dissipation coefficient K... T During this period, it can be treated as a constant and calculated using equation (3):

[0061] K T =λτ o γ (3),

[0062] τ0 represents the temperature rise of the heating element at t0.

[0063] Then, when t = t0, under the initial condition τ = τ0, equation (4) is obtained by integrating equation (1):

[0064]

[0065] The time constant T is determined by Definition. Since the parameters c, m, and A are undetermined, it is assumed that the time constant T is represented by equation (5):

[0066]

[0067] α and β are undetermined parameters.

[0068] The total heating power p of the heating element is related to the current, resistance, and other losses of the heating element. Therefore, in some embodiments, it is assumed that the total heating power p is represented by equation (6):

[0069]

[0070] η is an undetermined parameter that may be related to the skin effect or other factors of the heating element;

[0071] I represents the current in the heating element;

[0072] T amb Indicates ambient temperature;

[0073] ρ0 represents the resistivity of the heating element at 0℃.

[0074] It should be understood that in other embodiments, the total heating power p of the heating element may be expressed by other equations. The scope of this disclosure is not intended to be limited in this respect.

[0075] Then, by substituting equations (3), (5) and (6) into equation (4), we obtain equation (7):

[0076]

[0077] Equation (7) can be derived by setting And b = β, rewritten as equation (8):

[0078]

[0079] Furthermore, a, b, γ, and d are undetermined parameters.

[0080] Equation (8) is the result of integrating equation (1) over the time interval from t0 to t1 when t = t0, under the initial condition τ = τ0.

[0081] In some embodiments, the constraints of equation (8) may be set as a∈(0, 1000], b∈[-1000, 1000], γ∈[0, 0.45], d∈[0, 1]. The constraints are approximate parameter ranges derived from multiple experiments. In other embodiments, the constraints of equation (8) may be set as other ranges. The scope of this disclosure is not intended to be limited in this respect.

[0082] Equation (8) can be rewritten in a more general form as expressed by equation (9):

[0083]

[0084] τ n Indicates at t n Temperature rise of the heating element;

[0085] τ n-1 Indicates at t n-1 Temperature rise of the heating element;

[0086] I n-1 Indicates at t n-1 The current in the heating element;

[0087] T ambn-1 Indicates at t n-1 The ambient temperature;

[0088] Δt=t n -t n-1 Indicates t n With t n-1 The time interval between them.

[0089] The constraints of equation (9) can be the same as those of equation (8), i.e., a∈(0, 1000], b∈[-1000, 1000], γ∈[0, 0.45], d∈[0, 1].

[0090] Since the parameters a, b, γ, and d are undetermined, the above model needs to be pre-trained to determine these parameters. Figure 2The illustration shows a flowchart of a method 200 for training a model for predicting the temperature rise of a heating element in a switching device, according to an embodiment of the present disclosure.

[0091] like Figure 2 As shown, method 200 includes: at 210, obtaining a model for predicting temperature rise. The model includes multiple inputs, outputs, and multiple parameters to be determined. In an embodiment, the model is represented by equation (9) as described above. In equation (9), the model's output includes the temperature rise τ. n The model's inputs include the temperature rise τ n-1 Current I n-1 and ambient temperature T ambn-1 Furthermore, the parameters to be determined include parameters a, b, γ, and d.

[0092] To determine the parameters a, b, γ, and d, a model needs to be trained. To this end, method 200 further includes: at 220, acquiring n+1 sets of physical quantities related to the heating element. Under the normal operating state of the heating element, at n+1 time points t0, t1, ..., t..., each time step apart... n Each physical quantity is collected at a corresponding time point. Each set of physical quantities includes the current and actual temperature of the heating element, as well as the ambient temperature. Therefore, the n+1 sets of physical quantities include currents I0, I1, ..., I... n The actual temperature T of the heating element act0 T act1 ... T actn Ambient temperature T amb0 T amb1 ... T ambn .

[0093] The method also includes: at 230, based on the corresponding ambient temperature T amb0 T amb1 ... T ambn The actual temperature T in each group of physical quantities act0 T act1 ... T actn Converted to actual temperature rise τ act0 τ act1 、…、τ actn Specifically, the actual temperature rise τ act0 =T act0 -T amb0 Actual temperature rise τ act0 =T act0 -T amb0 Actual temperature rise τ actn =T actn -T ambn .

[0094] Then, at 240, currents I0, I1, ..., I can be used. n Actual temperature rise τ act0 τ act1 、…、τ actn and ambient temperature T amb0 T amb1 ... T ambn To train the model to determine the parameters a, b, γ, and d. Figure 3 The illustration shows a flowchart of training a model using current, actual temperature rise, and ambient temperature according to an embodiment of the present disclosure.

[0095] In some embodiments, such as Figure 3 As shown, training the model using current, actual temperature rise, and ambient temperature includes: at 2401, for each time step, using the currents I0, I1, ..., I at the start time point corresponding to the time step. n-1 Actual temperature rise τ act0 τ act1 、…、τ actn-1 and ambient temperature T amb0 T amb1 ... T ambn-1 As input to the model represented by equation (9), and using the actual temperature rise τ corresponding to the end time point of the time step. act1 、…、τ actn The model output is used to create equations to obtain n equations; and at 2402, the n equations are solved by least squares to determine the parameters a, b, γ and d.

[0096] In some embodiments, at 2401, each of the n equations is created using a discrete approximation scheme. In some embodiments, at 2402, the n equations are solved using the least squares method.

[0097] After determining the undetermined parameters a, b, γ and d, the trained model represented by equation (9) can be used to progressively determine the temperature rise of the heating element. Figure 4 The illustration shows a flowchart of a method 400 for determining the temperature rise of a heating element in a switching device according to an embodiment of the present disclosure.

[0098] like Figure 4 As shown, method 400 includes: predicting the temperature rise of a heat-generating element in a switching device using a model trained by method 200. During the prediction of the temperature rise, only the real-time current of the heat-generating element, the time interval, and the ambient temperature need to be obtained, and then the temperature rise of the heat-generating element can be predicted iteratively using equation (9). Figure 5 The illustration shows a flowchart of predicting the temperature rise of a heating element using a model according to an embodiment of the present disclosure. Figure 5As shown, predicting the temperature rise of the heating element using a model includes: at 4101, acquiring the real-time current of the heating element and the ambient temperature acquired at a first time step; and at 4102, predicting the temperature rise of the heating element in the first time step by inputting the real-time current, the ambient temperature, and the predicted temperature rise in a second time step prior to the first time step into the model. Through these embodiments, the temperature rise in a current time step can be reliably predicted by using the current, the ambient temperature, and the predicted temperature rise in previous time steps.

[0099] Specifically, at 4102, during the time period from t0 to t1, the data can be based on the real-time current I0, temperature rise τ0, and ambient temperature T. amb0 The temperature rise τ1 is calculated using equation (9); during the time period from t1 to t2, it can be calculated based on the real-time current I1, the temperature rise τ1, and the ambient temperature T. amb1 The temperature rise τ2 is calculated using equation (9); and from t n-1 to t n During the time period, it can be based on the real-time current I n-1 Temperature rise τ n-1 and ambient temperature T ambn-1 The temperature rise τ is calculated using equation (9). n Temperature rise τ1, τ2, and τ n This can be represented by equations (10), (11), and (12) respectively:

[0100]

[0101]

[0102] ...

[0103]

[0104] The model trained by method 200 can be used not only to predict the transient temperature rise of the heating element at any time point, but also to predict the steady-state temperature rise of the heating element under any current. According to equation (1), when the temperature rise of the heating element becomes stable under any current, dτ will be equal to 0. Therefore, the steady-state temperature rise τ of I under any current is... w It can be expressed by equation (13):

[0105]

[0106] According to an embodiment of Method I, both the time constant as a function of temperature rise and the dynamic current load are considered when building the model. The model trained by Method 200 can be used to predict transient or steady-state temperature rise under any current load. This model is designed with strong physical constraints and few parameters, preventing overfitting on most switching device operating loads. Through these embodiments, the downtime of switching devices can be reduced and the reliability of switching devices can be improved.

[0107] Return to reference Figure 4 In some embodiments, method 400 further includes: at 420, acquiring the real-time temperature of the heating element collected in a first time step; at 430, converting the real-time temperature of the heating element into a real-time temperature rise based on the ambient temperature; and at 440, triggering an alarm in response to the difference between the real-time temperature rise and the predicted temperature rise exceeding a predetermined threshold. During operation of the switching device 100, the real-time temperature rise detected by the sensor can be compared with the predicted temperature rise to monitor whether the actual temperature rise of the heating element deviates from the predicted temperature rise. Through these embodiments, abnormal temperature rises in the switching device 100 can be detected in a timely manner, thereby enabling corresponding maintenance to be performed on the switching device.

[0108] Figure 6 An example test arrangement for a switching device 100 according to an embodiment of the present disclosure is illustrated. Figure 6 As shown, the first feeder panel 610, the second feeder panel 620, and the third feeder panel 630 are arranged from left to right. Feeder panels 610 and 620 are connected by double D-shaped rods 640, while the third feeder panel 630 is not connected. Current enters the switchgear 100 from the second feeder panel 620 and exits the switchgear 100 from the first feeder panel 610. Thermocouples (not shown) are arranged on the contacts of the switchgear 100 (such as...). Figure 1 The real-time temperature of the busbar contact 101, circuit breaker upper contact finger 102, circuit breaker lower contact finger 103 and cable contact 104 shown is collected.

[0109] The test currents are listed in Table 1 below. In some embodiments, the currents marked 3 to 16, excluding marks 6, 7, 11, and 12a shown in Table 1, are selected as the training set, and the currents marked 17 to 22 are selected as the validation set. The training set contains 43% of the data, and the validation set contains 57% of the data.

[0110] Table 1

[0111]

[0112]

[0113] Based on the detected current, time interval, and ambient temperature, the predicted temperature rise is as follows: Figures 7 to 8 As shown in the image.

[0114] Figure 7 (a) The illustration shows the predicted temperature rise of the bus contacts of phase A on the first feeder panel 610. Figure 7 The solid line in (a) indicates the measured temperature rise of the A-phase busbar contact. Figure 7 The dashed line in (a) indicates the predicted temperature rise of the A-phase busbar contacts.

[0115] Figure 7 (b) The figure shows the predicted temperature rise of the contact fingers on the circuit breaker of phase A on the first feeder panel 610. Figure 7 The solid line in (b) indicates the measured temperature rise of the contact fingers on phase A circuit breaker. Figure 7 The dashed line in (b) indicates the predicted temperature rise of the contacts on the A-phase circuit breaker.

[0116] Figure 7 (c) The figure shows the predicted temperature rise of the lower contact finger of the circuit breaker in phase A on the first feeder panel 610. Figure 7 The solid line in (c) indicates the measured temperature rise of the lower contact finger of the A-phase circuit breaker. Figure 7 The dashed line in (c) indicates the predicted temperature rise of the lower contact finger of the A-phase circuit breaker.

[0117] Figure 7 (d) illustrates the predicted temperature rise of the cable contacts of phase A on the first feeder panel 610. Figure 7 The solid line in (d) indicates the measured temperature rise of the A-phase cable contact. Figure 7 The dashed line in (d) indicates the predicted temperature rise of the A-phase cable contact.

[0118] Figure 8 (a) The illustration shows the predicted temperature rise of the bus contacts of phase A on the first feeder panel 620. Figure 8 The solid line in (a) indicates the measured temperature rise of the A-phase busbar contact. Figure 8 The dashed line in (a) indicates the predicted temperature rise of the A-phase busbar contacts.

[0119] Figure 8 (b) The figure shows the predicted temperature rise of the contact fingers on the circuit breaker of phase A on the first feeder panel 620. Figure 8 The solid line in (b) indicates the measured temperature rise of the contact fingers on phase A circuit breaker. Figure 8 The dashed line in (b) indicates the predicted temperature rise of the contacts on the A-phase circuit breaker.

[0120] Figure 8 (c) The figure shows the predicted temperature rise of the lower contact finger of the circuit breaker in phase A on the first feeder panel 620. Figure 8 The solid line in (c) indicates the measured temperature rise of the lower contact finger of the A-phase circuit breaker. Figure 8 The dashed line in (c) indicates the predicted temperature rise of the lower contact finger of the A-phase circuit breaker.

[0121] Figure 8 (d) illustrates the predicted temperature rise of the cable contacts of phase A on the first feeder panel 620. Figure 8 The solid line in (d) indicates the measured temperature rise of the A-phase cable contact. Figure 8 The dashed line in (d) indicates the predicted temperature rise of the A-phase cable contact.

[0122] Table 2 illustrates the prediction errors for temperature rise of the busbar contacts, upper circuit breaker contacts, lower circuit breaker contacts, and cable contacts of phases A, B, and C on panels 610 and 620. As can be seen from Table 2, the absolute prediction error is less than 2.90°C in all cases. The overall average prediction errors for panels 610 and 620 are correspondingly 0.94°C and 0.52°C. These errors are acceptable in practical applications.

[0123] Table 2

[0124]

[0125]

[0126] Method II

[0127] Method II provides a different way to solve equation (1). In particular, by substituting equation (2) into equation (1), equation (14) is obtained:

[0128] pdt=λAτ 1 +γdt+cmdτ (14).

[0129] Then, by substituting equation (6) into equation (14), we obtain equation (15):

[0130]

[0131] Equation (15) can be derived by setting... and Rewritten as equation (16):

[0132]

[0133] g, f, and γ are undetermined parameters.

[0134] It can be done as follows Figure 2 and Figure 3The method 200 shown is used to train the model represented by equation (16) to determine the parameters g, f, and γ. Except that each of the n equations is created using the Runge-Kutta iterative method, the training process of the model represented by equation (16) is similar to that of the model represented by equation (9). Therefore, the specific training process of the model represented by equation (16) will not be described in detail here.

[0135] After determining the undetermined parameters g, f, and γ, the trained model represented by equation (16) can be used, for example, by using... Figure 4 and Figure 5 The method 400 shown is used to progressively determine the temperature rise of the heating element. The specific prediction process for the transient temperature rise of the heating element can be calculated using the Runge-Kutta iterative method.

[0136] Furthermore, the model represented by equation (16) can be used not only to predict the transient temperature rise of the heating element at any point in time, but also to predict the steady-state temperature rise of the heating element under any current. According to equation (16), when the temperature rise of the heating element becomes stable under any current, It will equal 0. Therefore, the steady-state temperature rise τ under any current will be 0. w It can be expressed by equation (17):

[0137]

[0138] In some embodiments of this disclosure, such as Figure 9 As shown, an apparatus 900 for training a model for predicting and / or determining temperature rise is provided according to embodiments of the present disclosure. The apparatus 900 may include a computer processor 910 coupled to a computer-readable storage unit 920, and the storage unit 920 includes instructions 922. When executed by the computer processor 910, the instructions 922 may cause the computer processor 910 to implement methods 200 and 400 as described in the preceding paragraphs, and details will be omitted hereinafter.

[0139] According to embodiments of this disclosure, methods 200 and 400 are not limited to being implemented by a local processor, but can be implemented by a remote processor. For example, methods 200 and 400 can be implemented at a cloud computing node. In particular, data collected on-site can be transmitted to and processed at the cloud computing node. The computation results can then be returned from the cloud computing node to the local device or system. In this way, it is not necessary to provide additional computing equipment on-site.

[0140] In some embodiments, each of methods 200 and 400 may be implemented by a single processor (e.g., an MCU or a cloud computing node). In other embodiments, each of methods 200 and 400 may be implemented by multiple processors. For example, some actions of methods 200 and 400 may be implemented locally by an MCU, while other actions of methods 200 and 400 may be implemented remotely by a cloud computing node. The scope of this disclosure is not intended to be limited in this respect.

[0141] In some embodiments of this disclosure, a computer-readable medium is provided. The computer-readable medium has instructions stored thereon, and when executed on at least one processor, the instructions cause at least one processor to perform the methods 200 and 400 described in the preceding paragraphs, and details will be omitted below.

[0142] In some embodiments of this disclosure, a computer program product is provided. This computer program product includes instructions that, when executed on at least one processor, cause the at least one processor to perform methods 200 and 400 as described in the preceding paragraphs, and details will be omitted hereinafter.

[0143] Generally, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. Although some aspects of the embodiments of this disclosure are illustrated and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, as non-limiting examples, the blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0144] Program code for performing the methods of this disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that, when executed by the processor or controller, the program code enables the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0145] The above-described program code can be implemented on a machine-readable medium, which can be any tangible medium that includes or stores a program used by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. More specific examples of machine-readable storage media will include electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0146] Furthermore, although the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific or sequential order shown, or requiring all shown operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although numerous specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure, but rather as descriptions of features that may be characteristic of particular embodiments. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. On the other hand, the various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0147] Although the subject matter has been described in language specifically used for structural features and / or methodological actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as examples of implementing the claims.

Claims

1. A method for training a model to predict the temperature rise of a heating element in a switching device, comprising: Obtain a model for predicting the temperature rise, the model including multiple inputs, outputs and multiple parameters to be determined; Obtain n+1 sets of physical quantities related to the heating element. Each set of physical quantities is collected at one time point among n+1 time points under the normal operating state of the heating element. The n+1 time points are spaced apart by a time step. Each set of physical quantities includes the current and actual temperature of the heating element and the ambient temperature. Based on the corresponding ambient temperature, the actual temperature in each group of physical quantities is converted into the actual temperature rise; as well as The model is trained using the current, the actual temperature rise, and the ambient temperature to determine the plurality of parameters.

2. The method according to claim 1, wherein training the model using the current, the actual temperature rise, and the ambient temperature comprises: For each time step, n equations are created as follows: using the current, the actual temperature rise, and the ambient temperature corresponding to the start time of the time step as the input to the model, and using the actual temperature rise corresponding to the end time of the time step as the output of the model; and Solve the n equations to determine the plurality of parameters.

3. The method according to claim 2, Each of the n equations is created using a discrete approximation scheme or the Runge-Kutta iterative method, and / or The n equations are solved using the least squares method.

4. The method according to any one of claims 1 to 3, wherein the heating element comprises at least one of the following: busbar contact, circuit breaker upper contact finger, circuit breaker lower contact finger, and cable contact.

5. A method for determining the temperature rise of a heating element in a switching device, the method comprising: The temperature rise of the heating element in the switching device is predicted using a model trained by the method according to any one of claims 1 to 4.

6. The method of claim 5, wherein predicting the temperature rise of the heating element using the model comprises: The real-time current and ambient temperature of the heating element are acquired within the first time step. as well as The temperature rise of the heating element in the first time step is predicted by inputting the real-time current, the ambient temperature, and the predicted temperature rise in the second time step prior to the first time step into the model.

7. The method according to claim 6, further comprising: Obtain the real-time temperature of the heating element collected during the first time step; The real-time temperature of the heating element is converted into a real-time temperature rise based on the ambient temperature. as well as An alarm is triggered in response to the difference between the real-time temperature rise and the predicted temperature rise exceeding a predetermined threshold.

8. An apparatus for training a model for predicting the temperature rise of a heating element in a switching device, the apparatus comprising: At least one processor; as well as At least one memory, including instructions stored thereon, which, when executed by the at least one processor, cause the at least one processor to perform actions, the actions including the following: Obtain a model for predicting the temperature rise, the model including multiple inputs, outputs and multiple parameters to be determined; Obtain n+1 sets of physical quantities related to the heating element. Each set of physical quantities is collected at one time point out of n+1 time points under the normal operating state of the heating element. The n+1 time points are spaced apart by a time step. Each set of physical quantities includes the current and actual temperature of the heating element and the ambient temperature. Based on the corresponding ambient temperature, the actual temperature in each group of physical quantities is converted into the actual temperature rise; as well as The model is trained using the current, the actual temperature rise, and the ambient temperature to determine the plurality of parameters.

9. The apparatus of claim 8, wherein training the model using the current, the actual temperature rise, and the ambient temperature comprises: For each time step, n equations are created as follows: using the current, the actual temperature rise, and the ambient temperature corresponding to the start time of the time step as the input to the model, and using the actual temperature rise corresponding to the end time of the time step as the output of the model; and Solve the n equations to determine the plurality of parameters.

10. The apparatus according to claim 9, Each of the n equations is created using a discrete approximation scheme or the Runge-Kutta iterative method, and / or The n equations are solved using the least squares method.

11. An apparatus for determining the temperature rise of a heating element in a switching device, the apparatus comprising: At least one processor; as well as At least one memory includes instructions stored thereon that, when executed by the at least one processor, cause the at least one processor to perform an action, the action including the following: The temperature rise of the heating element in the switching device is predicted using a model trained by using the apparatus according to any one of claims 8 to 10.

12. The apparatus of claim 11, wherein predicting the temperature rise of the heating element using the model comprises: The real-time current and ambient temperature of the heating element are acquired within the first time step. as well as The temperature rise of the heating element in the first time step is predicted by inputting the real-time current, the ambient temperature, and the predicted temperature rise in the second time step prior to the first time step into the model.

13. The apparatus of claim 12, wherein the action further comprises: Obtain the real-time temperature of the heating element collected during the first time step; The real-time temperature of the heating element is converted into a real-time temperature rise based on the ambient temperature. as well as An alarm is triggered in response to the difference between the real-time temperature rise and the predicted temperature rise exceeding a predetermined threshold.

14. The apparatus according to any one of claims 8 to 13, wherein the at least one processor comprises at least one of a local processor or a remote processor, and The remote processor mentioned above includes cloud computing nodes.

15. A computer-readable storage medium having instructions stored thereon, the instructions, when executed by at least one processor, causing the at least one processor to perform the method according to any one of claims 1 to 7.

Images