System for monitoring a circuit breaker

Abstract

The invention relates to a system for monitoring a circuit breaker, the system comprising: at least one sensor; and a processing unit; wherein the at least one sensor is configured to be positioned and utilized to obtain at least one sensor data of a main shaft of the operable circuit breaker; wherein the at least one sensor is configured to provide the at least one sensor data of the main shaft of the operable circuit breaker to the processing unit; and wherein the processing unit is configured to determine position and / or velocity information of a movable contact of the operable circuit breaker, wherein the determination comprises an analysis of the at least one sensor data of the main shaft of the operable circuit breaker by a trained neural network implemented by the processing unit.

Description

TECHNICAL FIELD

[0001] The present invention relates to a system for monitoring a circuit breaker, a system for monitoring a two- or three-phase switching device or control device, a method for monitoring a circuit breaker, a system for training a neural network for monitoring a circuit breaker, and a method for training a neural network for monitoring a circuit breaker. BACKGROUND

[0002] The operating mechanism of a circuit breaker (CB) is one of the main subsystems that are prone to failure of the switching device. Most of the mechanical failure modes occurring in the mechanism can be detected by monitoring the travel curve, which represents the position of the moving contact. In addition, the travel curve can also reveal electrical failure modes like contact erosion.

[0003] Today, travel curve monitoring is rarely used in switching devices.

[0004] Furthermore, the existing solutions have the following disadvantages:

[0005] [1] Most of today's travel curve monitoring solutions use only the measurement of the main shaft angle and calculate the position of the moving contact by representing the kinematic relationship of all three poles. Therefore, it cannot distinguish between the travel curves of the three poles. Thus, it is difficult to identify the location of the fault, e.g., in which pole.

[0006] [2] In medium voltage (MV) CBs, the push rod is the preferred measurement location for the travel curve. Therefore, the requirements on the sensor and the required electrical components for the connection are high due to the CB design in the installation space, and the commissioning is very complex. Therefore, only a few position sensor solutions are considered.

[0007] [3] The selected position sensor for the travel curve measurement has to withstand the resulting impact vibrations due to the switching operation, which reduces the service life of the sensor. In general, the sensor should reliably measure the travel curve during the service life of the CB.

[0008] [1] - [3] are the characteristics of a position sensor suitable for travel curve measurement in CBs and can only be mitigated by selecting high-end solutions. This usually results in much higher costs, which makes permanent equipment unattractive.

[0009] There is a need to address these issues. SUMMARY

[0010] It would therefore be advantageous to have an improved technology for monitoring a circuit breaker.

[0011] In a first aspect, a system for monitoring a circuit breaker is provided. The system comprises:

[0012] at least one sensor; and

[0013] a processing unit.

[0014] The at least one sensor is configured to be positioned and utilized to obtain at least one sensor data of a main shaft of the operable circuit breaker. The at least one sensor is configured to provide the at least one sensor data of the main shaft of the operable circuit breaker to the processing unit. The processing unit is configured to determine position and / or velocity information of a movable contact of the operable circuit breaker, wherein the determining comprises analysis of the at least one sensor data of the main shaft of the operable circuit breaker by a trained neural network implemented by the processing unit.

[0015] In an example, the neural network is trained based on at least one sensor data of a main shaft of a calibration circuit breaker and at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker.

[0016] In an example, the at least one sensor data of the main shaft of the calibration circuit breaker is acquired at a same time as the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker.

[0017] In an example, the calibration circuit breaker is of a same type or model as the operable circuit breaker.

[0018] In an example, the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is of a same type or model as the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0019] In an example, the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is positioned at a same or equivalent at least one position as the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0020] In an example, the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker comprises one or more of: an acceleration sensor; a main shaft angle sensor.

[0021] In an example, the at least one sensor utilized to obtain the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker comprises one or more of: a position sensor; a velocity sensor.

[0022] In an example, the position information and / or the velocity information of the movable contact comprises a travel curve.

[0023] In an example, the system comprises an output unit configured to output position information and / or speed information of the movable contact.

[0024] In an example, the processing unit is configured to determine whether the circuit breaker has a fault, wherein the determination comprises an analysis of the position information and / or speed information of the movable contact.

[0025] In a second aspect, there is provided a system for monitoring a two- or three-phase switching device or control device. The system comprises two or three systems according to the first aspect, one for each phase of the two- or three-phase.

[0026] In a third aspect, there is provided a method for monitoring a circuit breaker, the method comprising:

[0027] a) utilizing at least one sensor positioned to obtain at least one sensor data of a main shaft of the operable circuit breaker;

[0028] b) providing the at least one sensor data of the main shaft of the operable circuit breaker to a processing unit; and

[0029] c) determining, by the processing unit, position and / or speed information of a movable contact of the operable circuit breaker, wherein the determination comprises an analysis of the at least one sensor data of the main shaft of the operable circuit breaker by a trained neural network implemented by the processing unit.

[0030] In a fourth aspect, there is provided a system for training a neural network for monitoring a circuit breaker, the system comprising:

[0031] - at least one first sensor;

[0032] - at least one second sensor; and

[0033] - a processing unit.

[0034] The at least one first sensor is configured to be positioned and utilized to obtain at least one sensor data of a main shaft of the calibration circuit breaker. The at least one first sensor is configured to provide the at least one sensor data of the main shaft of the calibration circuit breaker to the processing unit. The at least one second sensor is configured to be positioned and utilized to obtain at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker. The at least one second sensor is configured to provide the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker to the processing unit. The processing unit is configured to train a neural network. The training of the neural network comprises utilizing the at least one sensor data of the main shaft of the calibration circuit breaker and the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker. The trained neural network is configured to determine position and / or velocity information of a movable contact of an operable circuit breaker based on an analysis of at least one sensor data of a main shaft of the operable circuit breaker.

[0035] In a fifth aspect, a method for training a neural network for monitoring a circuit breaker is provided, the method comprising:

[0036] a1) utilizing at least one first sensor positioned to obtain at least one sensor data of a main shaft of a calibration circuit breaker;

[0037] b1) providing the at least one sensor data of the main shaft of the calibration circuit breaker to a processing unit;

[0038] c1) utilizing at least one second sensor positioned to obtain at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker;

[0039] d1) providing the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker to the processing unit; and

[0040] e1) training, by the processing unit, a neural network, wherein the training of the neural network comprises utilizing the at least one sensor data of the main shaft of the calibration circuit breaker and the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker, and wherein the trained neural network is configured to determine position and / or velocity information of a movable contact of an operable circuit breaker based on an analysis of at least one sensor data of a main shaft of the operable circuit breaker.

[0041] The above aspects and examples will become apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0042] The exemplary embodiments will be described hereinafter with reference to the following drawings:

[0043] Figure 1A schematic representation of an exemplary system for monitoring a circuit breaker is shown;

[0044] Figure 2 A schematic representation of an exemplary system for monitoring a two- or three-phase switching device or control device is shown;

[0045] Figure 3 A method for monitoring a circuit breaker is shown;

[0046] Figure 4 A schematic representation of an exemplary system for training a neural network for monitoring a circuit breaker is shown;

[0047] Figure 5 A method for training a neural network for monitoring a circuit breaker is shown; and

[0048] Figure 6 A workflow for training of a neural network is shown. DETAILED DESCRIPTION

[0049] Figure 1 An example of a system 10 for monitoring a circuit breaker is shown. The system comprises at least one sensor 20 and a processing unit 30. The at least one sensor is configured to be positioned and utilized to obtain at least one sensor data of a main shaft of an operable circuit breaker 40. The at least one sensor is configured to provide the at least one sensor data of the main shaft of the operable circuit breaker to the processing unit. The processing unit is configured to determine position and / or velocity information of a movable contact of the operable circuit breaker. The determination comprises an analysis of the at least one sensor data of the main shaft of the operable circuit breaker by a trained neural network implemented by the processing unit.

[0050] According to an example, the neural network is trained based on at least one sensor data of a main shaft of a calibration circuit breaker 50 and at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker.

[0051] According to an example, the at least one sensor data of the main shaft of the calibration circuit breaker is acquired at the same time as the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker.

[0052] According to an example, the calibration circuit breaker is of the same type or model as the operable circuit breaker.

[0053] According to an example, the at least one sensor 20, 60 utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is of the same type or model as the at least one sensor 20 utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0054] According to an example, the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the calibrated circuit breaker is positioned at the same or equivalent at least one position as the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0055] According to an example, the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker comprises one or more of: an acceleration sensor; a main shaft angle sensor.

[0056] According to an example, the at least one sensor 70 utilized to obtain the at least one sensor data of the movable contact and / or push rod of the calibrated circuit breaker comprises one or more of: a position sensor; a speed sensor.

[0057] According to an example, the position information and / or speed information of the movable contact comprises a travel curve.

[0058] According to an example, the system comprises an output unit configured to output the position information and / or speed information of the movable contact.

[0059] According to an example, the processing unit is configured to determine whether the circuit breaker has a fault. The determination comprises an analysis of the position information and / or speed information of the movable contact.

[0060] Figure 2 An example of a system 100 for monitoring a two- or three-phase switching device or control device is shown. The system comprises two or three systems 10 as described above in relation to Figure 1 the description, wherein there is one system 10 for each phase of the two- or three-phase circuit breaker.

[0061] Figure 3 A method 200 for monitoring a circuit breaker in its basic steps is shown. The method comprises:

[0062] In a utilizing step 210, also referred to as step a), at least one sensor is utilized, the at least one sensor being positioned to obtain at least one sensor data of a main shaft of an operable circuit breaker;

[0063] In a providing step 220, also referred to as step b), the at least one sensor data of the main shaft of the operable circuit breaker is provided to a processing unit; and

[0064] In a determining step 230, also referred to as step c), a position and / or speed information of a movable contact of the operable circuit breaker is determined by the processing unit, wherein the determination comprises an analysis of the at least one sensor data of the main shaft of the operable circuit breaker by a trained neural network implemented by the processing unit.

[0065] In an example, the neural network is trained based on at least one sensor data of a main shaft of the calibration circuit breaker and at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker.

[0066] In an example, the at least one sensor data of the main shaft of the calibration circuit breaker is acquired at the same time as the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker.

[0067] In an example, the calibration circuit breaker and the operable circuit breaker are of the same type or model.

[0068] In an example, the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is of the same type or model as the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0069] In an example, the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is positioned at the same or equivalent at least one position as the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0070] In an example, the at least one sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker comprises one or more of: an acceleration sensor; a main shaft angle sensor.

[0071] In an example, the at least one sensor utilized to obtain the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker comprises one or more of: a position sensor; a speed sensor.

[0072] In an example, the position information and / or the speed information of the movable contact comprises a travel curve.

[0073] In an example, the system comprises an output unit and the method comprises outputting the position information and / or the speed information of the movable contact.

[0074] In an example, the method comprises determining, by the processing unit, whether the circuit breaker has a fault, wherein the determination comprises analyzing the position information and / or the speed information of the movable contact.

[0075] Figure 4An example of a system 300 for training a neural network for monitoring a circuit breaker is shown. The system comprises at least one first sensor 20, 60, at least one second sensor 70, and a processing unit 30, 80. The at least one first sensor is configured to be positioned and utilized to obtain at least one sensor data of a main shaft of a calibration circuit breaker 50. The at least one first sensor is configured to provide the at least one sensor data of the main shaft of the calibration circuit breaker to the processing unit. The at least one second sensor is configured to be positioned and utilized to obtain at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker. The at least one second sensor is configured to provide the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker to the processing unit. The processing unit is configured to train a neural network. The training of the neural network comprises utilizing the at least one sensor data of the main shaft of the calibration circuit breaker and the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker. The trained neural network is configured to determine position and / or velocity information of the movable contact of an operable circuit breaker 40 based on an analysis of at least one sensor data of a main shaft of the operable circuit breaker.

[0076] In an example, the at least one sensor data of the main shaft of the calibration circuit breaker is obtained at a same time as the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker.

[0077] In an example, the calibration circuit breaker is of a same type or model as the operable circuit breaker.

[0078] In an example, the at least one first sensor (20, 60) utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is of a same type or model as the at least one sensor (20) that will be utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0079] In an example, the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is positioned at a same or equivalent at least one position as the at least one sensor that will be utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0080] In an example, the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker comprises one or more of: an acceleration sensor; a main shaft angle sensor.

[0081] In an example, the at least one second sensor (70) utilized to obtain the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker comprises one or more of: a position sensor; a velocity sensor.

[0082] In an example, the position information and / or the speed information of the movable contact comprises a travel curve.

[0083] Figure 5 A method 400 for training a neural network for monitoring a circuit breaker in its basic steps is shown. The method comprises:

[0084] In a utilizing step 410, also referred to as step al), at least one first sensor is utilized, the at least one first sensor being positioned to obtain at least one sensor data of a main shaft of a calibration circuit breaker;

[0085] In a providing step 420, also referred to as step bl), the at least one sensor data of the main shaft of the calibration circuit breaker is provided to a processing unit;

[0086] In a utilizing step 430, also referred to as step cl), at least one second sensor is utilized, the at least one second sensor being positioned to obtain at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker;

[0087] In a providing step 440, also referred to as step dl), the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker is provided to the processing unit; and

[0088] In a training step 450, also referred to as step el), the neural network is trained by the processing unit. The training of the neural network comprises utilizing the at least one sensor data of the main shaft of the calibration circuit breaker and the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker. The trained neural network is configured to determine position and / or speed information of a movable contact of an operable circuit breaker based on an analysis of at least one sensor data of a main shaft of the operable circuit breaker.

[0089] In an example, the method comprises acquiring the at least one sensor data of the main shaft of the calibration circuit breaker at the same time as the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker.

[0090] In an example, the calibration circuit breaker is of the same type or model as the operable circuit breaker.

[0091] In an example, the at least one first sensor (20, 60) utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is of the same type or model as the at least one sensor (20) to be utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0092] In an example, the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is positioned at the same or equivalent at least one position as the at least one sensor that will be utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

[0093] In an example, the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker comprises one or more of: an acceleration sensor; a main shaft angle sensor.

[0094] In an example, the at least one second sensor (70) utilized to obtain the at least one sensor data of the movable contact and / or push rod of the calibration circuit breaker comprises one or more of: a position sensor; a speed sensor.

[0095] In an example, the position information and / or speed information of the movable contact comprises a travel curve.

[0096] Reference is now made to Figure 6 In particular details, a system for monitoring a circuit breaker, a system for monitoring a two or three phase switching device or control device, a method for monitoring a circuit breaker, a system for training a neural network for monitoring a circuit breaker and a method for training a neural network for monitoring a circuit breaker are described.

[0097] The state monitoring and diagnosis of the operating mechanism of a circuit breaker (CB) is mainly based on travel curve measurements. The reason is that most of the fault modes can be captured by position or speed sensors that measure the travel curve. However, acquiring this data is difficult to achieve due to the need for robust sensors that meet the installation space and service life requirements of the CB.

[0098] The inventors realized that other types of sensors such as accelerometers that are more suitable and can be more easily installed in the CB can be utilized in a completely different and new way to get this travel curve information. The inventors have applied a method of artificial intelligence (AI) for extracting the position of the moving contact for each pole from this other sensor data (e.g. accelerometer) and thus enable CB drive monitoring based on the travel curve. In addition to mechanical faults, the resulting travel curve can also be used to monitor electrical fault modes with respect to instance contact erosion.

[0099] The solution involves the use of a sequence-to-sequence artificial intelligence (AI) model that first learns to produce travel curve data from other sensor data by training on samples that contain travel curves and other sensor measurements (e.g. accelerometers), rotary encoders for measuring the main shaft angle, etc.

[0100] Subsequently, the model can extract travel curve information also with respect to data not used for training the model and when travel curve information is not available. The accuracy of this approach is assessed in two ways:

[0101] 1. The generated travel curve is compared to the actual travel curve using data not used for training the model and using all samples (e.g. mean squared error using all samples).

[0102] 2. Using data not used for training the model by computing features describing properties of the travel curve that are important for the health diagnosis and known from scientific literature, and comparing the features computed using the generated travel curve to the features computed using the actual travel curve.

[0103] Thus, the solution utilizes a dataset with travel curve signals and other sensor data, which are recorded simultaneously from the same device. An artificial intelligence (AI) model is then used for learning to generate a travel curve from other sensor data, which is taken simultaneously with the travel curve signal, which can be accelerometer signals, angle measurements of the main shaft, etc.

[0104] Subsequently, the model is used to extract travel curve information also with respect to data not used for training the model and when travel curve information is not available. Thus, the travel curve data can be generated only for "other sensor data" such as from an accelerometer, which can be placed and used more conveniently for new circuit breakers of the same type or model as used for generating the neural network model.

[0105] Thus, after training the model, the model can be used to diagnose the health of the circuit breaker drive using only measurement data from sensors.

[0106] Figure 6 An overview workflow of the above described technique is provided.

[0107] While the application has been illustrated and described in detail in the drawings and foregoing description, the illustrations and description are to be considered illustrative or exemplary and not restrictive. The application is not limited to the disclosed embodiments. Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a study of the drawings, the disclosure, and the appended claims.

Claims

1. A system (10) for monitoring a circuit breaker, the system comprising: - at least one first sensor; and - a processing unit; wherein the at least one first sensor is configured to be positioned and utilized to obtain at least one sensor data of a main shaft of an operable circuit breaker (40), wherein the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker comprises one or more of: an acceleration sensor, a main shaft angle sensor; wherein the at least one first sensor is configured to provide the at least one sensor data of the main shaft of the operable circuit breaker to the processing unit; and wherein the processing unit is configured to determine position and / or velocity information of a movable contact and / or a push rod of the operable circuit breaker, wherein the position and / or the velocity information of the movable contact and / or the push rod comprises a travel curve, characterized in that the determination comprises an analysis of the at least one sensor data of the main shaft of the operable circuit breaker by a trained neural network implemented by the processing unit; wherein the neural network is trained based on at least one sensor data of a main shaft of a calibration circuit breaker (50) and at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker, wherein the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker comprises one or more of: an acceleration sensor, a main shaft angle sensor, wherein the at least one second sensor (70) utilized to obtain the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker comprises one or more of: a position sensor, a velocity sensor.

2. The system according to claim 1, wherein the at least one sensor data of the main shaft of the calibration circuit breaker is acquired at the same time as the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker.

3. The system according to any one of claims 1 to 2, wherein the calibration circuit breaker is of the same type or model as the operable circuit breaker.

4. The system according to any one of claims 1 to 2, wherein at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker is positioned at the same or equivalent at least one position as the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker.

5. The system according to any one of claims 1 to 2, wherein the system comprises an output unit configured to output the position information and / or the velocity information of the movable contact and / or the push rod.

6. The system according to any one of claims 1 to 2, wherein the processing unit is configured to determine whether the circuit breaker has a fault, wherein the determination comprises an analysis of the position information and / or the speed information of the movable contact and / or push rod.

7. A system (100) for monitoring a two- or three-phase switching device or control device, the system comprising two or three systems (10) according to any one of claims 1 to 6, one system for each phase of the two- or three-phase.

8. A method (200) for monitoring a circuit breaker, the method comprising: a) utilizing at least one first sensor, the at least one first sensor being positioned to obtain at least one sensor data of a main shaft of an operable circuit breaker, wherein the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker comprises one or more of: an acceleration sensor, a main shaft angle sensor; b) providing the at least one sensor data of the main shaft of the operable circuit breaker to a processing unit; and c) determining, by the processing unit, position and / or speed information of a movable contact and / or push rod of the operable circuit breaker, characterized in that the determination comprises an analysis of the at least one sensor data of the main shaft of the operable circuit breaker by a trained neural network implemented by the processing unit, wherein the neural network is trained based on at least one sensor data of a main shaft of a calibration circuit breaker and at least one sensor data of a movable contact and / or push rod of the calibration circuit breaker, wherein the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker comprises one or more of: an acceleration sensor, a main shaft angle sensor, wherein the at least one first sensor utilized to obtain at least one sensor data of the movable contact and / or push rod of the calibration circuit breaker comprises one or more of: a position sensor, a speed sensor, wherein the position and / or the speed information of the movable contact and / or push rod comprises a travel curve.

9. A system (300) for training a neural network for monitoring a circuit breaker, the system comprising: - at least one first sensor; - at least one second sensor (70); and - a processing unit; wherein the at least one first sensor is configured to be positioned and utilized to obtain at least one sensor data of a main shaft of a calibration circuit breaker (50), wherein the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker comprises one or more of: an acceleration sensor, a main shaft angle sensor; wherein the at least one first sensor is configured to provide the at least one sensor data of the main shaft of the calibration circuit breaker to the processing unit; wherein the at least one second sensor is configured to be positioned and utilized to obtain at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker, wherein the at least one second sensor utilized to obtain the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker comprises one or more of: a position sensor, a speed sensor; wherein the at least one second sensor is configured to provide the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker to the processing unit; and characterized in that the processing unit is configured to train a neural network, wherein the training of the neural network comprises utilization of the at least one sensor data of the main shaft of the calibration circuit breaker and the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker, and wherein the trained neural network is configured to determine position and / or speed information of a movable contact and / or a push rod of an operable circuit breaker (40) based on analysis of at least one sensor data of a main shaft of the operable circuit breaker, and wherein the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker comprises one or more of: an acceleration sensor, a main shaft angle sensor, wherein the position and / or the speed information of the movable contact and / or the push rod comprises a travel curve.

10. A method (400) for training a neural network for monitoring a circuit breaker, the method comprising: al) utilizing at least one first sensor positioned to obtain at least one sensor data of a main shaft of a calibration circuit breaker, wherein the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the calibration circuit breaker comprises one or more of: an acceleration sensor, a main shaft angle sensor; bl) providing the at least one sensor data of the main shaft of the calibration circuit breaker to a processing unit; cl) utilizing at least one second sensor positioned to obtain at least one sensor data of a movable contact and / or a push rod of the calibration circuit breaker, wherein the at least one second sensor utilized to obtain the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker comprises one or more of: a position sensor, a speed sensor; dl) providing the at least one sensor data of the movable contact and / or the push rod of the calibration circuit breaker to the processing unit; and e1) characterized in that the method comprises training, by the processing unit, a neural network, wherein the training of the neural network comprises utilizing the at least one sensor data of the main shaft of the calibration circuit breaker and the at least one sensor data of the movable contact and / or push rod of the calibration circuit breaker, and wherein the trained neural network is configured to determine, based on an analysis of at least one sensor data of a main shaft of an operable circuit breaker, position and / or velocity information of a movable contact and / or push rod of the operable circuit breaker, and wherein the at least one first sensor utilized to obtain the at least one sensor data of the main shaft of the operable circuit breaker comprises one or more of: an acceleration sensor, a main shaft angle sensor, wherein the position and / or the velocity information of the movable contact and / or push rod comprises a travel curve.

Images