CN115600477A - Electronic device and method for arranging sensor on equipment - Google Patents

Abstract

An electronic device and method for mounting a sensor on a device are provided. The method comprises the following steps: positioning a first sensor at a first location of the device and a second sensor at a second location of the device; acquiring first sensing data through a first sensor and acquiring second sensing data through a second sensor; inputting the first sensing data to the energy model to generate first restored data, and inputting the second sensing data to the energy model to generate second restored data; calculating a first energy between the first sensing data and the first restored data, and calculating a second energy between the second sensing data and the second restored data; a first proposed position is generated based on the first energy and the second energy, wherein the first proposed position is one of the first position and the second position. The electronic device and the method can select the suggested position on the equipment suitable for arranging the sensor.

Description

Electronic device and method for arranging sensor on equipment

Technical Field

The invention relates to an electronic device and a method for arranging a sensor on equipment.

Background

In order to monitor the equipment, a person can arrange a plurality of sensors at different positions of the equipment so as to obtain sensing data corresponding to the different positions. Based on cost considerations, it is an important issue in the art how to obtain the most information measured by the equipment with the least number of sensors. The process of achieving this often requires extensive knowledge and trial and error. For example, in order to detect the vibration condition of the industrial equipment, a professional with deep understanding and experience of the industrial equipment needs to select candidate positions of a plurality of vibration sensors from the industrial equipment. Then, the practitioner should select a plurality of positions where the most amount of information can be obtained by trial and error, so as to install the plurality of vibration sensors at the plurality of positions, respectively. The above-mentioned method requires the involvement of a professional and his experience. On the other hand, the experience of the professional cannot be adapted to different kinds of equipment. Therefore, when different kinds of devices need to be monitored, a plurality of people with different fields and professions need to participate in the installation process of the sensor, and the cost required to be invested is high.

Disclosure of Invention

The invention provides an electronic device and a method for arranging a sensor on equipment, which can select a suggested position suitable for arranging the sensor on the equipment.

The invention relates to an electronic device for arranging a sensor on equipment, which comprises a first sensor, a second sensor, a transceiver, a storage medium and a processor. The first sensor is arranged at a first position of the equipment. The second sensor is arranged at a second position of the equipment. The storage medium stores an energy model. The processor is coupled to the storage medium, the transceiver, the first sensor and the second sensor, wherein the processor is configured to perform: acquiring first sensing data through a first sensor and acquiring second sensing data through a second sensor; inputting the first sensing data to the energy model to generate first restored data, and inputting the second sensing data to the energy model to generate second restored data; calculating a first energy between the first sensing data and the first restored data, and calculating a second energy between the second sensing data and the second restored data; generating a first proposed position based on the first energy and the second energy, wherein the first proposed position is one of the first position and the second position; and outputting, by the transceiver, the first proposed position.

The invention discloses a method for arranging a sensor on equipment, which comprises the following steps: positioning a first sensor at a first location of the device and a second sensor at a second location of the device; acquiring first sensing data through a first sensor and acquiring second sensing data through a second sensor; inputting the first sensing data to the energy model to generate first restored data, and inputting the second sensing data to the energy model to generate second restored data; calculating a first energy between the first sensing data and the first restored data, and calculating a second energy between the second sensing data and the second restored data; generating a first proposed position based on the first energy and the second energy, wherein the first proposed position is one of the first position and the second position; and outputting the first proposed position.

Based on the above, the electronic device of the present invention can train a corresponding energy model based on training data obtained from a specific location of the equipment, and analyze sensing data obtained from other locations of the equipment by using the energy model. The electronic device may determine whether the sensed data measured from the specific location and the other locations has the most data diversity (variety) according to the analysis result.

Drawings

Fig. 1 is a schematic diagram of an electronic device according to an embodiment of the invention.

FIG. 2 is a schematic diagram of an apparatus according to an embodiment of the invention.

FIG. 3 is a flow chart illustrating a method for mounting a sensor to an apparatus according to one embodiment of the invention.

Detailed Description

In order that the present disclosure may be more readily understood, the following specific examples are given as illustrative of the invention which may be practiced in various ways. Further, wherever possible, the same reference numbers are used in the drawings and the description to refer to the same or like parts.

Fig. 1 is a schematic diagram of an electronic device 100 according to an embodiment of the invention. The electronic device 100 is configured to obtain the sensing data with the most data diversity from the equipment by installing the sensor on the equipment. The electronic device 100 may comprise a processor 110, a storage medium 120, a transceiver 130, and N sensors, where N is any positive integer. The N sensors may include sensor 141, sensor 142, sensor 143, 8230, sensor N, etc. The electronic device 100 can analyze the recommended position suitable for the sensor to be set from the equipment, wherein the recommended position is the position in the equipment where the sensing data with the most data diversity can be obtained.

The processor 110 is, for example, a Central Processing Unit (CPU), or other programmable general purpose or special purpose Micro Control Unit (MCU), a microprocessor (microprocessor), a Digital Signal Processor (DSP), a programmable controller, an Application Specific Integrated Circuit (ASIC), an Arithmetic Logic Unit (ALU), a Complex Programmable Logic Device (CPLD), a Field Programmable Gate Array (FPGA), or other similar components or combinations thereof. The processor 110 may be coupled to the storage medium 120, the transceiver 130, the sensor 141, the sensor 142, the sensor 143, and the sensor N via a wireless (e.g., wiFi, bluetooth, etc.) or wired (cable) connection, and access and execute a plurality of software (software), modules, and various applications stored in the storage medium 120.

The storage medium 120 is, for example, any type of fixed or removable Random Access Memory (RAM), read-only memory (ROM), flash memory (flash memory), hard Disk Drive (HDD), solid State Drive (SSD), or the like, or any combination thereof, and is used for storing a plurality of software, modules, or various applications executable by the processor 110.

The transceiver 130 transmits and receives signals in a wireless or wired manner. The transceiver 130 may also perform operations such as low noise amplification, impedance matching, frequency mixing, frequency up or down conversion, filtering, amplification, and the like.

The sensor 141 (or the sensors 142, 143, N) is, for example, an image sensor, an accelerometer, an inertial measurement unit, a vibration sensor, a magnetometer, a thermometer, a hygrometer, a flow meter, a flow rate meter, a liquid level meter, a pressure gauge, an ultraviolet sensor, an infrared sensor, an ultrasonic sensor, a pH sensor, an illuminance sensor, a distance meter, or a displacement sensor, but the invention is not limited thereto.

Fig. 2 shows a schematic diagram of the apparatus 20 according to an embodiment of the invention. The device 20 is, for example, a fan, but the invention is not limited thereto. In the present embodiment, it is assumed that the number N of sensors of the electronic device 100 is equal to 3. That is, the electronic device 100 may include 3 sensors, i.e., the sensor 141, the sensor 142, and the sensor 143. The sensors 141, 142 and 143 may be located at a position 21, a position 22 and a position 23, respectively, of the device, where the position 21 is, for example, the center of the front end of the fan housing, the position 22 is, for example, one of the upper edges of the fan, and the position 23 is, for example, another of the upper edges of the fan. The processor 110 can obtain the first sensing data corresponding to the position 21 through the sensor 141, obtain the second sensing data corresponding to the position 22 through the sensor 142, and obtain the third sensing data corresponding to the position 23 through the sensor 143. The first sensing data, the second sensing data or the third sensing data is, for example, vibration data of a fan, but the invention is not limited thereto. In one embodiment, the sensor 141 and the sensor 142 (or the sensor 143) may be the same sensor. Therefore, a single sensor 141 can be used to obtain sensing data corresponding to different positions respectively. For example, after the sensor 141 acquires the first sensing data corresponding to the position 21, the sensor 141 may be moved to the position 22 to acquire the second sensing data. Therefore, the electronic device 100 only needs a single sensor 141 to obtain the first sensing data corresponding to the position 21 and the second sensing data corresponding to the position 22, which is not limited by the invention.

In the present embodiment, the user determines in advance to set a sensor at the position 23 corresponding to the sensor 143, thereby measuring the state of the apparatus 20. The processor 110 may train an energy-based model (energy-based model) according to the third sensing data obtained by the sensor 143 and store the energy model in the storage medium 120. The energy model may be used to extract characteristics (e.g., vibration frequency, etc.) in the input data (third sensing data), and restore the input data according to the characteristics, thereby outputting restored data corresponding to the input data. The energy model may include a self-encoded neural network (auto encoder neural network) model, a constrained Boltzmann machine (RBM), or a Deep Belief Network (DBN), but the invention is not limited thereto. The loss function of the energy model is, for example, the energy between the input data and the restored data corresponding to the input data, wherein the energy between the input data and the restored data is, for example, the Mean Square Error (MSE) between the input data and the restored data, but the invention is not limited thereto.

After generating the energy model corresponding to the location 23, the processor 110 may input the first sensing data corresponding to the location 21 to the energy model to generate first recovery data. Then, the processor 110 may calculate a first energy between the first sensing data and the first recovery data. The first energy may include a mean square error between the first sensing data and the first restored data, but the present invention is not limited thereto.

In one embodiment, the first sensing data and the first restoring data are optimized. Before the processor 110 inputs the first sensing data into the energy model, the processor 110 may perform signal smoothing on the first sensing data to generate first smoothed data. The processor 110 may then input the first smoothed data to the energy model to generate first restored data. After generating the first recovery data, the processor 110 may perform signal smoothing on the first recovery data to generate second smooth data. The processor 110 may calculate a first energy corresponding to between the first sensing data and the first restoring data according to the first smoothing data and the second smoothing data.

In one embodiment, the processor 110 may perform filtering on the first sensing data to generate first filtered data before the processor 110 inputs the first sensing data into the energy model. The processor 110 may then input the first filtered data to the energy model to generate first recovered data. After generating the first reduced data, the processor 110 may perform filtering on the first reduced data to generate second filtered data. The processor 110 may calculate a first energy corresponding to between the first sensing data and the first restored data according to the first filtered data and the second filtered data.

Alternatively, the processor 110 may input second sensing data corresponding to the position 22 to the energy model to generate second recovery data. Then, the processor 110 may calculate a second energy between the second sensing data and the second recovery data. The second energy may include a mean square error between the second sensing data and the second restored data, but the present invention is not limited thereto.

In one embodiment, the second sensing data and the second restore data are optimized. Before the processor 110 inputs the second sensing data into the energy model, the processor 110 may perform signal smoothing on the second sensing data to generate third smoothed data. The processor 110 may then input the third smoothed data to the energy model to generate second restored data. After generating the second recovery data, the processor 110 may perform signal smoothing on the second recovery data to generate fourth smoothed data. The processor 110 may calculate a second energy corresponding to the second sensing data and the second restoring data according to the third smoothed data and the fourth smoothed data.

In one embodiment, the processor 110 may perform filtering on the second sensing data to generate third filtered data before the processor 110 inputs the second sensing data into the energy model. The processor 110 may then input the third filtered data to the energy model to generate second restored data. After generating the second reduced data, the processor 110 may perform filtering on the second reduced data to generate fourth filtered data. The processor 110 may calculate a second energy corresponding to the second sensing data and the second restored data according to the third filtered data and the fourth filtered data.

In other embodiments, after obtaining a first energy between the first sensing data and the first recovery data and a second energy between the second sensing data and the second recovery data, the processor 110 may generate a first proposed position according to the first energy and the second energy, wherein the first proposed position may be one of the position 21 and the position 22.

Specifically, the processor 110 may compare the first energy and the second energy. If the first energy is greater than the second energy, it represents that the correlation between the feature of the first sensing data and the feature of the third sensing data is smaller than the correlation between the feature of the second sensing data and the feature of the third sensing data. In other words, the data diversity between the first sensing data and the third sensing data is greater than the data diversity between the second sensing data and the third sensing data. Thus, having determined that the sensor is disposed at location 23, processor 110 may determine that disposing another sensor at location 21 is more beneficial than disposing another sensor at location 22. Accordingly, the processor 110 may set the first suggested position to a position 21 corresponding to the first energy in response to the first energy being greater than the second energy. For the fan, the data diversity includes, for example, the vibration amplitude, vibration frequency, material characteristics, etc., but the invention is not limited thereto.

The processor 110 may output the first proposed position for reference by the user through the transceiver 130.

FIG. 3 is a flow chart of a method for disposing a sensor in an apparatus, wherein the method can be implemented by the electronic device 100 shown in FIG. 1, according to an embodiment of the invention. In step S301, a first sensor is disposed at a first location of the device, and a second sensor is disposed at a second location of the device. In step S302, first sensing data is obtained by the first sensor, and second sensing data is obtained by the second sensor. In step S303, the first sensing data is input to the energy model to generate first restored data, and the second sensing data is input to the energy model to generate second restored data. In step S304, a first energy between the first sensing data and the first restored data is calculated, and a second energy between the second sensing data and the second restored data is calculated. In step S305, a first proposed position is generated based on the first energy and the second energy, wherein the first proposed position is one of the first position and the second position. In step S306, a first suggested position is output.

In summary, the electronic apparatus of the present invention can train the corresponding energy model based on the training data obtained from the specific location of the device, and analyze the sensing data obtained from other locations of the device by using the energy model. If the energy between the sensed data and the training data is larger, it represents that the diversity between the training data and the sensed data is higher. Therefore, the electronic device can prompt a user to arrange the sensors at the specific position and the other positions respectively so as to obtain the maximum data amount of the equipment.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the invention, which is defined by the claims and the description of the invention, and all simple equivalent changes and modifications made therein are also within the scope of the invention. Furthermore, it is not necessary for any embodiment or claim of the invention to address all of the objects, advantages, or features disclosed herein. In addition, the abstract and the title of the disclosure are provided to facilitate the search of patent documents and are not intended to limit the scope of the disclosure. Furthermore, the terms "first," "second," and the like, as used herein or in the appended claims, are used merely to name elements (elements) or to distinguish one embodiment or range from another, and are not intended to limit the upper or lower limit on the number of elements.

Description of the reference numerals

100 electronic device

110 processor

120 storage medium

130 transceiver

141. 142, 143, N sensors

S301, S302, S303, S304, S305, S306.

Claims (9)

1. An electronic device for mounting a sensor on a device, the electronic device comprising:

the first sensor is arranged at a first position of the equipment;

the second sensor is arranged at a second position of the equipment;

a transceiver;

a storage medium storing an energy model; and

a processor coupled to the storage medium, the transceiver, the first sensor, and the second sensor, wherein the processor is configured to perform:

acquiring first sensing data through the first sensor and acquiring second sensing data through the second sensor;

inputting the first sensing data to the energy model to generate first restored data, and inputting the second sensing data to the energy model to generate second restored data;

calculating a first energy between the first sensing data and the first restored data, and calculating a second energy between the second sensing data and the second restored data;

generating a first proposed position based on the first energy and the second energy, wherein the first proposed position is one of the first position and the second position; and

outputting, by the transceiver, the first proposed position.

2. The electronic device of claim 1, wherein the processor sets the first suggested position to the first position corresponding to the first energy in response to the first energy being greater than the second energy.

3. The electronic device of claim 1, wherein the energy model comprises one of: a self-coding neural network model, a constrained boltzmann machine, and a deep belief network.

4. The electronic device of claim 1, further comprising:

a third sensor disposed at a third position of the apparatus, wherein

The processor obtains third sensing data from the third sensor and trains the energy model according to the third sensing data.

5. The electronic device of claim 4, wherein the processor is configured to further perform:

setting the third position as a second suggested position; and

outputting, by the transceiver, the second suggested position.

6. The electronic device of claim 1, wherein the processor is configured to further perform:

performing signal smoothing on the first sensing data to generate first smoothed data, and performing the signal smoothing on the first restored data to generate second smoothed data; and

and calculating the first energy according to the first smoothing data and the second smoothing data.

7. The electronic device of claim 1, wherein the processor is configured to further perform:

performing filtering on the first sensing data to generate first filtered data, and performing the filtering on the first restored data to generate second filtered data; and

the first energy is calculated according to the first filtering data and the second filtering data.

8. The electronic device of claim 1, wherein the first sensor comprises one of: an image sensor, an accelerometer, an inertial measurement unit, a vibration sensor, a magnetometer, a thermometer, a hygrometer, a flow meter, a flow rate meter, a liquid level meter, a pressure meter, an ultraviolet sensor, an infrared sensor, an ultrasonic sensor, a pH sensor, an illuminance sensor, a range finder, and a displacement sensor.

9. A method for positioning a sensor on a device, the method comprising:

positioning a first sensor at a first location of the device and a second sensor at a second location of the device;

acquiring first sensing data through the first sensor and second sensing data through the second sensor;

inputting the first sensing data to an energy model to generate first restored data, and inputting the second sensing data to the energy model to generate second restored data;

calculating a first energy between the first sensed data and the first restored data, and calculating a second energy between the second sensed data and the second restored data;

generating a first proposed position based on the first energy and the second energy, wherein the first proposed position is one of the first position and the second position; and

outputting the first suggested location.

Images