Automation equipment evaluation optimization method and system

Abstract

The invention provides an automatic equipment evaluation optimization method and system, and the method comprises the steps: obtaining the judgment information of equipment and a corresponding initial sensing signal; capturing a periodic signal from the initial sensing signal; calculating the periodic signal to obtain at least one initial characteristic parameter; calculating the judgment information and the at least one initial characteristic parameter to obtain corresponding initial weight information; and establishing an evaluation model according to the at least one initial characteristic parameter and the initial weight information, and executing the method by an automatic equipment evaluation optimization system to monitor the equipment in real time, accurately analyze the operation state of the equipment and detect the abnormality.

Description

Technical Field

[0001] The present invention relates to an evaluation method and a system thereof, and in particular to an automation equipment evaluation and optimization method and a system thereof. Background Art

[0002] In the past, before / during / after the operation of the production line, it may be necessary to inspect and maintain the machines and equipment used. Most of these inspections and maintenance require manpower to confirm whether the inspection index is abnormal or find out the causes that may cause the abnormality, so as to ensure that each machine is in a state that can be produced, but it is impossible to know the actual situation of the equipment. When the actual production starts, since the equipment is not 100% in good condition, it is necessary to rely on on-site personnel to observe the equipment in real time to ensure that the equipment can operate normally. This method may not be able to determine in real time which part of the equipment has a problem. Generally speaking, it is mostly when it is found that the production capacity speed is not good, the production line is stuck or the defective rate is increased that the on-site personnel will confirm which link has a problem. In this way, a lot of manpower and long waiting time are required, which not only increases time and labor costs, but also fails to efficiently grasp the status of the equipment.

[0003] The precision equipment in the production line is complex and of many types. If you want to monitor the status of different equipment, you need to propose corresponding solutions to meet the monitoring needs of the equipment. Similarly, engineers who maintain the machines need to be familiar with various solutions, or different equipment sections are maintained by different engineers. This method still cannot achieve integrated management.

[0004] Furthermore, if the data from monitoring equipment is imported into the AI ​​model, it will take a long time to accumulate a large amount of monitoring data and events in order to achieve the purpose of monitoring and evaluation. In addition, a large amount of data needs to be cleaned according to different factory processes. Different products, processes, parameters, actions, etc. will have different data, and each type of data requires professionals to construct a corresponding analysis model. This also means that each analysis model is exclusive to a specific production line and cannot be used universally, and its construction cost will be very high.

[0005] To this end, the present invention provides an automated equipment evaluation optimization method and system thereof, which performs calculations based on the acquired sensing signals and inputs the generated characteristic parameters into the evaluation model, so as to obtain the corresponding evaluation results, thereby obtaining the overall health status of the machine and whether there are any abnormal conditions, and can also predict whether maintenance procedures need to be performed, etc. It can be applied to all periodic equipment monitoring, has high versatility, greatly reduces construction costs, and effectively manages monitoring conditions. Summary of the invention

[0006] The main purpose of the present invention is to provide an automated equipment evaluation and optimization method to automatically track the sensing signals of the equipment, evaluate the equipment status in real time, and accurately grasp the current and future status of the equipment.

[0007] Another object of the present invention is to provide an automated equipment evaluation and optimization system, wherein after the processing module obtains characteristic parameters from the sensing signal, the monitoring module can perform evaluation to achieve the purpose of real-time monitoring.

[0008] In order to achieve the above-mentioned purpose, an embodiment of the present invention discloses an automated equipment evaluation optimization method, the steps of which include: obtaining judgment information of the equipment and a corresponding initial sensing signal; extracting a periodic signal from the initial sensing signal; calculating the periodic signal to obtain at least one initial characteristic parameter; calculating the judgment information and the at least one initial characteristic parameter to obtain corresponding initial weight information; and establishing an evaluation model using the at least one initial characteristic parameter and the initial weight information.

[0009] In a preferred embodiment, the method comprises the steps of: capturing a sensing signal; computing the sensing signal to obtain at least one corresponding characteristic parameter; and inputting the at least one characteristic parameter into the evaluation model to generate a corresponding evaluation result.

[0010] In a preferred embodiment, the sensing signal and the initial sensing signal are selected from a vibration signal, a current signal, a pressure signal, a torque signal or a combination thereof.

[0011] In a preferred embodiment, the at least one characteristic parameter and the at least one initial characteristic parameter are selected from amplitude, frequency, phase, wavelet, standard deviation, stability or a combination thereof.

[0012] In a preferred embodiment, the evaluation result includes operation analysis information, anomaly detection information and operation trend information of the device.

[0013] In order to achieve the other purpose mentioned above, an embodiment of the present invention discloses an automated equipment evaluation and optimization system, comprising: an operation processing module, which obtains a sensing signal of the equipment and performs operations based on the sensing signal to obtain at least one characteristic parameter; and a monitoring module, which is signal-connected to the operation processing module, receives and performs evaluation based on the at least one characteristic parameter to obtain a corresponding evaluation result.

[0014] In a preferred embodiment, a display interface is included, which is connected to the monitoring module signal to display the evaluation results. The display interface includes an equipment overall scoring area, an equipment status management area, and an equipment operation trend management area. The equipment overall scoring area displays the operation analysis information of the equipment, the equipment status management area displays abnormality detection information, and the equipment operation trend management area displays operation trend information.

[0015] In a preferred embodiment, a monitoring device is included, which is signal-connected to the computing processing module and is used to detect the device to obtain the corresponding sensing signal, wherein the sensing signal is selected from a vibration signal, a current signal, a pressure signal, a torque signal or a combination of the above.

[0016] In a preferred embodiment, the at least one characteristic parameter is selected from amplitude, frequency, phase, wavelet, standard deviation, stability or a combination thereof.

[0017] In a preferred embodiment, the calculation processing module obtains the judgment information of the device and the corresponding initial sensing signal for calculation, and captures the periodic signal from the initial sensing signal, and obtains the at least one initial characteristic parameter and the corresponding initial weight information from the judgment information and the periodic signal. According to the at least one initial characteristic parameter and the initial weight information, an evaluation model is established and transmitted to the monitoring module, so that the monitoring module evaluates the sensing signal through the evaluation model to obtain the corresponding evaluation result.

[0018] The beneficial effect of the present invention is to monitor the overall health of the machine and whether there are any abnormal conditions in real time. It can be applied to all periodic equipment monitoring, has high versatility, greatly reduces the construction cost, and effectively manages the monitoring situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1A is a method flow chart of an embodiment of the present invention;

[0020] Figure 1B A partial method flow chart of an embodiment of the present invention;

[0021] Figure 2 is a system schematic diagram of an embodiment of the present invention;

[0022] Figure 3A A schematic diagram of an implementation process of an embodiment of the present invention;

[0023] Figure 3B A schematic diagram of an implementation process of an embodiment of the present invention;

[0024] Figure 3C A schematic diagram of an implementation process of an embodiment of the present invention;

[0025] Figure 3D A schematic diagram of an implementation process of an embodiment of the present invention;

[0026] Figure 3E A schematic diagram of an implementation process of an embodiment of the present invention;

[0027] Figure 3F A schematic diagram of an implementation process of an embodiment of the present invention;

[0028] Figure 3G A schematic diagram of an implementation process of an embodiment of the present invention;

[0029] Figure 3H A schematic diagram of an implementation process of an embodiment of the present invention;

[0030] Fig. 3I is a schematic diagram of an implementation process of an embodiment of the present invention; and

[0031] Figure 3J The figure is a schematic diagram of an implementation process of an embodiment of the present invention. DETAILED DESCRIPTION

[0032] To make the above and / or other purposes, effects, and features of the present invention more obvious and understandable, preferred embodiments are specifically described below in detail:

[0033] See also Figure 1A to Figure 1B , which is a method flow chart and a partial method flow chart of an embodiment of the present invention. As shown in the figure, the automation equipment evaluation and optimization method of the present invention comprises the following steps:

[0034] Step S1: Obtaining the judgment information of the device and the corresponding initial sensing signal;

[0035] Step S2: extracting a periodic signal from the initial sensing signal;

[0036] Step S3: Calculate the periodic signal to obtain at least one initial characteristic parameter;

[0037] Step S4: Calculating the determination information and the at least one initial feature parameter to obtain corresponding initial weight information; and

[0038] Step S5: Establishing an evaluation model using the at least one initial feature parameter and the initial weight information.

[0039] As shown in step S1, the judgment information of the device and the corresponding initial sensing signal are obtained to track the actual operation status of each round of the device. In one embodiment, the initial sensing signal can be a vibration signal, a current signal, a pressure signal, a torque signal, or a combination thereof. The initial sensing signal can select different types of sensing signals according to different device operation modes, so it is not limited thereto.

[0040] As shown in step S2, a periodic signal is captured from the initial sensing signal, wherein the periodic signal is a signal obtained according to each cycle of the operation of the device. For example, when the device is a robotic arm, the cycle is from the beginning to the end of each round of action, and each cycle is a repeated action. Therefore, the signal obtained in each cycle is also repeated, but not limited to this.

[0041] As shown in step S3, an operation is performed based on the periodic signal to obtain initial characteristic parameters. In one embodiment, the initial characteristic parameters can be amplitude, frequency, phase, wavelet, standard deviation, stability or a combination of the above. Similarly, when the initial sensing signal is a vibration signal, a fast Fourier transform (FFT) can be used for operation and analysis to generate information such as amplitude, frequency and phase.

[0042] As shown in step S4, calculations are performed based on the aforementioned judgment information and initial feature parameters to obtain corresponding initial weight information, that is, different weights are determined based on the initial feature parameters corresponding to each round of actions, so that the evaluation results can be more accurate, but not limited to this.

[0043] As shown in step S5, an evaluation model is established based on the aforementioned initial feature parameters and initial weight information. In this way, different weight distributions can be provided according to the feature parameters actually emphasized in each round of action, making the evaluation model more accurate.

[0044] Furthermore, the implementation method of the evaluation model of an embodiment of the present invention may include the following steps:

[0045] Step S6: capturing sensing signals;

[0046] Step S7: Calculate the sensing signal to obtain at least one corresponding characteristic parameter; and

[0047] Step S8: Input the at least one characteristic parameter into the evaluation model to generate a corresponding evaluation result.

[0048] As shown in step S6, a corresponding sensing signal is obtained when the device is operating. In one embodiment, the sensing signal can be a vibration signal, a current signal, a pressure signal, a torque signal, or a combination of the above. The sensing signal can select different types of sensing signals according to different device operation modes, so it is not limited here.

[0049] As shown in step S7, calculations are performed based on the sensing signal to obtain corresponding characteristic parameters. In one embodiment, the characteristic parameters may be amplitude, frequency, phase, wavelet, standard deviation, stability, or a combination thereof. When the sensing signal is a vibration signal, fast Fourier transform (FFT) may be used for calculation and analysis to generate information such as amplitude, frequency, and phase.

[0050] As shown in step S8, the characteristic parameters obtained by the above calculation are input into the evaluation model to obtain the evaluation results. In one embodiment, the evaluation model can generate a score by giving corresponding weights according to the characteristic parameters. The evaluation results can be presented in the form of numbers, text, symbols or charts, but are not limited to this.

[0051] See also Figure 2 , which is a system schematic diagram of an embodiment of the present invention. As shown in the figure, the automated equipment evaluation and optimization system of the present invention comprises: an operation processing module 1, a monitoring module 2, a display interface 3 and a monitoring device 4, wherein the monitoring module 2 is respectively connected to the operation processing module 1 and the display interface 3 by signal, and the monitoring device 4 is connected to the operation processing module 1 by signal, and the details are as follows:

[0052] After obtaining the sensing signal of the device D, the operation processing module 1 performs operation according to the sensing signal to obtain the corresponding characteristic parameters. In one embodiment, the characteristic parameters are selected from amplitude, frequency, phase, wavelet, standard deviation, stability or a combination of the above or a combination of the above, but not limited thereto.

[0053] In one embodiment, the operation processing module 1 obtains the judgment information and the corresponding initial sensing signal of the device D for operation, and extracts the periodic signal from the initial sensing signal, and obtains the initial characteristic parameters and the corresponding initial weight information from the judgment information and the periodic signal, and establishes and transmits the evaluation model to the monitoring module 2 based on the initial characteristic parameters and the initial weight information, wherein the initial sensing signal is composed of a plurality of repeated periodic signals, and each period is from the beginning to the end of each round of action of the device D on the production line, but is not limited to this.

[0054] The monitoring module 2 receives and evaluates the characteristic parameter to obtain a corresponding evaluation result. In one embodiment, the monitoring module 3 calculates and compares the sensing signal through an evaluation model to obtain a corresponding evaluation result.

[0055] The display interface 3 is used to display the evaluation results. In one embodiment, the display interface 3 includes an equipment overall scoring area 31, an equipment status management area 32, and an equipment operation trend management area 33. The equipment overall scoring area 31 displays the operation analysis information of the equipment D, the equipment status management area 32 displays the abnormality detection information, and the equipment operation trend management area 33 displays the operation trend information, but is not limited to this.

[0056] In one embodiment, the operation analysis information may be equipment health, equipment stability, number of vibration exceeding the standard, number of frequency exceeding the standard, actual operating status, and comprehensive score, but is not limited thereto.

[0057] In one embodiment, the abnormal detection information may be production line arm abnormality, automatic welding abnormality, forging die abnormality, stamping burr abnormality, lathe processing abnormality, drilling tool abnormality. Furthermore, the fault location or line can be determined based on the abnormal information, but it is not limited to this.

[0058] In one embodiment, the operation trend information may be an estimate of the trend of the future sensing signal based on the real-time monitoring signal, and a maintenance procedure may be arranged in advance to increase the service life of the equipment, but is not limited thereto.

[0059] The monitoring device 4 is used to detect the device D. After obtaining the sensing signal of the device D, it is transmitted to the operation processing module 1 for operation. In one embodiment, the monitoring device 4 can use different sensors according to the process characteristics to achieve accurate analysis and monitoring. Among them, the monitoring device 4 can be a vibration sensor, a current sensor, a pressure sensor or a combination of the above. For example, if the process is related to mechanical behavior, such as: a robot arm, a stamping and forging mold, a machine tool; if the process is directly related to the current, such as: automatic welding; if the process is directly related to the pressure, such as: automatic dispensing, gluing, injection molding, but not limited to this.

[0060] In one embodiment, the sensing signal is selected from a vibration signal, a current signal, a pressure signal, a torque signal or a combination thereof. The monitoring device 4 can be an additional device installed on the device D or can be an original monitoring device of the device D, but is not limited thereto.

[0061] To more clearly illustrate the operation process of an embodiment of the present invention, the following is described:

[0062] In one embodiment, the automated equipment evaluation optimization method and its system are applicable to industrial manufacturing equipment, such as semiconductor crystal growth, semiconductor manufacturing, semiconductor packaging, robotic arms, mechanical industry applications, panel manufacturing, PCB industry or automobile manufacturing, etc. The manufacturing equipment in these fields will use a large number of periodic production equipment. For example: processing machines, robotic arms, CNC machine tools, stamping and forging machine equipment, automatic welding arm equipment, injection molding machine equipment, etc. Therefore, the periodic production equipment will have certain actions, time and processes during operation or manufacturing. The method and its system use these repetitive actions to establish an evaluation model, but are not limited thereto.

[0063] When the process starts, the monitoring device 4 obtains the sensing signal of the device D. The sensing signal is a vibration signal for example. The change of vibration can be used to indicate the state change of the device D during actual operation. When the same action is performed, if the vibration signal changes, it usually indicates that there is a problem with the device D, so there is a force generated. This reason may come from various factors on the device D, such as poor balance, poor centering or bearing problems. The vibration on the device D is a mixed vibration, that is, it may be composed of a combination of vibration signals with different frequencies (Frequency), amplitudes (Amplitude), and phases (angles). Among them, the amplitude can be observed through three indicators, namely displacement (Displacement), velocity (Velocity) and acceleration (Acceleration), as shown in Table 1.

[0064] Table 1. Relevant parameters of vibration signal.

[0065]

[0066] In one embodiment, Fast Fourier transform (FFT) can be used to analyze vibration signals, and the vibration spectrum characteristics can be used to analyze the damaged parts and causes of damage. To this end, the changes in each frequency band of the spectrum generated by the action of the device D can be monitored, wherein the frequency band width can be set by itself. This monitoring method is suitable for equipment such as reducers, servo motors, slide rails, and screws, and a database is established with the obtained sensing signals to quickly inspect the actual conditions of each component in the equipment.

[0067] In one embodiment, the sensing signal reflects the health status of each component on the device D. If a single component is abnormal but has not yet affected the overall vibration amount, it may cause the measurement value of a single frequency band to be too large and generate an alarm, thereby achieving faster inspection and judgment.

[0068] In one embodiment, different characteristic parameters can be used to make judgments according to the process mode. Since the operation of the device D is extremely complex, normal signals and abnormal signals during operation are often intertwined. Therefore, the high or low value is no longer the criterion for judging whether the operation is abnormal. The initial value of a single value is obviously not sufficient.

[0069] In one embodiment, the characteristic parameters may be further calculated to present a variety of data types, which may be overall dynamic similarity (Dynamic Similarity), feature dynamic similarity (F-DynamicSimilarity), frequency over (Frequency Over), total spectrum dynamic similarity (SOA DynamicSimilarity), frequency similarity (Frequency Similarity), amplitude over (Amplitude Over) or a combination of the above.

[0070] The overall dynamic similarity is the degree of difference between the specific target action specification and the real-time measured sensing signal pattern. The total score can be calculated using 100 points as the benchmark.

[0071] The feature dynamic similarity (F-Dynamic Similarity) is the difference between the wave packet specification and the measured graph of a specific target action. The total score can be calculated using 100 points as the benchmark.

[0072] Frequency Over is the process of capturing the entire time-frequency graph during a specific target action sequence. Each spectrum graph has a spectrum standard established to calculate the excess and qualified ratios based on the total number of spectrum captured.

[0073] The overall spectrum dynamic similarity (SOA Dynamic Similarity) is to capture the entire time-frequency graph in the specific target action time segment, calculate the SOA value (Spectrum Overall value) with a single spectrum graph, and redraw the dynamic graph of the target action with each SOA value as the difference between the standard and the real-time measurement graph. The total score can be calculated using 100 points as the benchmark.

[0074] Frequency Similarity is the entire time-frequency diagram of the data captured in the specific target action timing segment. Each spectrum diagram has a spectrum standard established and is compared with the real-time spectrum under the relative timing. After each spectrum diagram is compared in sequence, the total score is calculated based on 100 points, and then calculated based on the average of the total number of spectra with 100 points as the benchmark.

[0075] Amplitude Over is to establish a global amplitude threshold upper limit for a specific target action, and use the number of data points as the matrix to calculate the number of times the real-time measurement action exceeds the standard, and then calculate the percentage based on the total number of data.

[0076] See also FIG. 3A to FIG. 3B, which is an evaluation result pattern of an embodiment of the present invention. Taking the tracking of each round of action of the automated robotic arm (operation action recognition Pass) as an example, it can be seen from the figure that it can be divided into an overall equipment scoring area 31, an equipment status management area 32 and an equipment operation trend management area 33. Among them, the overall equipment scoring area 31 displays the health score and stability score of the corresponding equipment, the equipment status management area 32 displays the aforementioned various data (data and charts), the equipment status management area 32 displays the actual operation status of multiple actions in the machine, and the equipment operation trend management area 33 presents the various data trends of the machine within a time period, and can also display predictive maintenance information.

[0077] See also FIG. 3C to FIG. 3D , which is an evaluation result pattern of an embodiment of the present invention. Taking the tracking of each round of action of the automated robotic arm (operation action recognition Pass) as an example, it can be seen from the figure that when each round of action includes action one and action two, the upper half will give scores for the health and stability of action one and action two, so that the user can more intuitively grasp the status of the device D. The lower half is the waveform of the sensing signal obtained corresponding to action one and action two. When the automated robotic arm operates normally, the machine learning action (yellow line part) is consistent with the real-time sensing signal (white line part).

[0078] See also FIG. 3E to FIG. 3F , which is an evaluation result pattern of an embodiment of the present invention. Taking the tracking of each round of action of the automated robotic arm (mechanical action abnormality, impact surge) as an example, it can be seen from the figure that when each round of action includes action one and action two, the overall dynamic similarity (Dynamic Similarity) shows that the machine learning action (yellow line part) and the real-time sensing signal (white line part) are quite different (such as the red circle), and the relevant sensing data can be further checked. In contrast, it can be seen that its health level has also decreased accordingly.

[0079] See also Figure 3G to Figure 3H , which is an evaluation result pattern of an embodiment of the present invention. Taking the tracking of each round of action of the automated robotic arm (mechanical micro-impact Pass) as an example, it can be seen from the figure that when each round of action includes action one and action two, the overall dynamic similarity (Dynamic Similarity) shows that the real-time sensing signal at the red circle (white line part) has a surge, but the health status has not decreased too much, but the stability has decreased slightly.

[0080] See also FIG. 3I to FIG. 3J, which is an evaluation result pattern of an embodiment of the present invention. Taking the tracking of each round of action of the automated robotic arm (mechanical slight jitter Pass) as an example, it can be seen from the figure that when each round of action includes action one and action two, the overall dynamic similarity (Dynamic Similarity) shows that the real-time sensing signal (white line part) has a continuous surge compared to the machine learning action (yellow line part), but the health status has not declined too much.

[0081] In summary, the present invention provides an automated equipment evaluation optimization method and system thereof, which performs calculations on each periodic signal in the sensing signal and generates evaluation results according to weights, thereby obtaining the overall real-time health status of the machine and whether there are any abnormal conditions. It can also be applied to all periodic equipment monitoring, and has high versatility and greatly reduces the construction cost, thereby achieving the purpose of the present invention.

[0082] However, what is described above is only a preferred embodiment of the present invention, but it cannot be used to limit the scope of patent protection of the present invention; therefore, all simple equivalent changes and modifications made according to the claims and the description of the present invention still fall within the scope of patent protection of the present invention.

[0083]

Explanation of symbols

[0084] 1. Computation and processing module

[0085] 2 Monitoring Module

[0086] 3 Display ports

[0087] 31 Equipment overall rating area

[0088] 32Device status management area

[0089] 33 Equipment operation trend management area

[0090] 4 Monitoring equipment

[0091] D Device

Claims

1. A method for optimizing automation equipment evaluation, characterized in that: The steps include: Obtaining the judgment information of the device and the corresponding initial sensing signal; Extracting a periodic signal from the initial sensing signal; Calculating the periodic signal to obtain at least one initial characteristic parameter; Calculating the determination information and the at least one initial feature parameter to obtain corresponding initial weight information; and An evaluation model is established using the at least one initial feature parameter and the initial weight information.

2. The automation equipment evaluation and optimization method according to claim 1, characterized in that: Contains steps: Capturing sensor signals; Calculating the sensing signal to obtain at least one corresponding characteristic parameter; and The at least one characteristic parameter is input into the evaluation model to generate a corresponding evaluation result.

3. The automation equipment evaluation and optimization method according to claim 1, characterized in that: The sensing signal and the initial sensing signal are selected from vibration signals, current signals, pressure signals, torque signals or a combination thereof.

4. The automation equipment evaluation and optimization method according to claim 1, characterized in that: The at least one characteristic parameter and the at least one initial characteristic parameter are selected from amplitude, frequency, phase, wavelet, standard deviation, stability or a combination thereof.

5. The automation equipment evaluation and optimization method according to claim 1, characterized in that: The evaluation results include operation analysis information, anomaly detection information and operation trend information of the equipment.

6. An automated equipment evaluation and optimization system, characterized in that: Include: A calculation processing module obtains a sensing signal of the device and performs calculations based on the sensing signal to obtain at least one characteristic parameter; and The monitoring module is connected to the operation processing module by signal, receives and evaluates the at least one characteristic parameter to obtain a corresponding evaluation result.

7. The automated equipment evaluation and optimization system according to claim 6, characterized in that: It includes a display interface, which is connected to the monitoring module signal to display the evaluation result. The display interface includes an equipment overall scoring area, an equipment status management area and an equipment operation trend management area. The equipment overall scoring area displays the operation analysis information of the equipment, the equipment status management area displays abnormal detection information, and the equipment operation trend management area displays operation trend information.

8. The automated equipment evaluation and optimization system according to claim 6, characterized in that: A monitoring device is included, which is signal-connected to the operation processing module and is used to detect the device to obtain the corresponding sensing signal, wherein the sensing signal is selected from a vibration signal, a current signal, a pressure signal, a torque signal or a combination of the above.

9. The automated equipment evaluation and optimization system according to claim 6, characterized in that: The at least one characteristic parameter is selected from amplitude, frequency, phase, wavelet, standard deviation, stability or a combination thereof.

10. The automated equipment evaluation and optimization system according to claim 6, characterized in that: The calculation processing module obtains the judgment information of the device and the corresponding initial sensing signal for calculation, and captures the periodic signal from the initial sensing signal, and obtains the at least one initial characteristic parameter and the corresponding initial weight information from the judgment information and the periodic signal. According to the at least one initial characteristic parameter and the initial weight information, an evaluation model is established and transmitted to the monitoring module, so that the monitoring module evaluates the sensing signal through the evaluation model to obtain the corresponding evaluation result.

Images