Direct current motor operation fault detection system based on artificial intelligence

Abstract

The invention belongs to the technical field of direct current motor operation supervision, and particularly relates to a direct current motor operation fault detection system based on artificial intelligence, which comprises a motor monitoring transmission module, a motor fault identification output module, a motor safety analysis module, a motor availability analysis module and a supervision terminal, according to the invention, the motor fault identification output module carries out analysis to determine whether the DC motor has a fault, and if the DC motor has a fault, a supervisor is reminded to timely take corresponding regulation and control measures for the DC motor according to needs; the operation safety of the direct current motor in the detection period is analyzed through the motor safety analysis module, and the availability of the direct current motor is analyzed through the motor availability analysis module when the motor safety early warning signal is generated, so that a supervisor can reasonably dispose the direct current motor and plan a subsequent supervision scheme; the management difficulty of supervisors is reduced, and safe and stable operation of the DC motor is ensured.

Description

Technical Field

[0001] The invention relates to the technical field of DC motor operation supervision, and in particular to a DC motor operation fault detection system based on artificial intelligence. Background Art

[0002] A DC motor is a rotating motor that can convert DC electrical energy into mechanical energy or mechanical energy into DC electrical energy. It is a motor that can realize the mutual conversion between DC electrical energy and mechanical energy. When it operates as a motor, it converts electrical energy into mechanical energy. When it operates as a generator, it converts mechanical energy into electrical energy. As an important power equipment, DC motors are widely used in various industrial and commercial fields.

[0003] During the operation of DC motors, the fault identification model is currently used to identify the operation faults based on the operation data of the DC motors. When the operation faults are not detected, the potential hidden dangers of the DC motors cannot be accurately fed back. It is also impossible to reasonably judge the use risk of the DC motors in a certain period of time and accurately analyze their availability when the use risk is judged to be high, which increases the difficulty of supervision for supervisors.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a DC motor operation fault detection system based on artificial intelligence, which solves the problems that the prior art cannot accurately feedback the potential operating hazards of the DC motor when no operating fault is detected, and cannot reasonably judge the use risk of the DC motor in a certain period and accurately analyze its availability when the use risk is judged to be high, and the operation supervision of the DC motor is difficult.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The artificial intelligence-based DC motor operation fault detection system includes a motor monitoring transmission module, a motor fault identification output module, a motor safety analysis module, a motor availability analysis module and a supervision terminal;

[0008] The motor monitoring transmission module monitors the operation of the DC motor, collects various operating data of the DC motor and sends them to the motor fault identification output module;

[0009] The motor fault identification output module analyzes various operating data of the motor based on the fault detection model of artificial intelligence to determine whether the DC motor has a fault. If it is determined that the DC motor has a fault, a fault warning signal is generated, and when the fault warning signal is generated, the monitoring terminal issues a corresponding warning;

[0010] The motor safety analysis module is used to set a detection period of L1, analyze the operation safety of the DC motor during the detection period, generate a motor safety qualification signal or a motor safety warning signal through analysis, and send the motor safety warning signal to the motor availability analysis module;

[0011] When the motor availability analysis module receives the motor safety warning signal, it performs availability analysis on the DC motor and generates a low availability signal or a high availability signal through analysis. When the motor safety warning signal or the low availability signal is generated, the monitoring terminal issues a corresponding warning.

[0012] Furthermore, the specific analysis process of the motor safety analysis module is as follows:

[0013] All faults occurring in the DC motor during the detection period are obtained, all faults are classified, and the corresponding type of fault is marked as a target fault i, where i is a natural number greater than 1; the number of times the target fault i occurs in the DC motor during the detection period is collected and marked as the initial fault value, and the ratio of the initial fault value to the total running time of the DC motor during the detection period is calculated to obtain the final fault value;

[0014] The fault final condition value is numerically compared with the corresponding preset fault final condition threshold. If the fault final condition value exceeds the preset fault final condition threshold, the target fault i is marked as a frequent fault; if the DC motor has frequent faults during the detection period, a motor safety abnormality signal is generated.

[0015] Furthermore, if there are no frequent faults in the DC motor during the detection period, the occurrence time of all faults in the DC motor during the detection period is obtained, and the occurrence time of the corresponding fault is marked as the identification time;

[0016] The interval between two adjacent groups of recognition moments is marked as the recognition interval, the recognition interval is numerically compared with the preset recognition interval threshold, the number of recognition intervals that do not exceed the preset recognition interval threshold during the detection period is counted and marked as the recognition interval low measurement value, and the number of recognition interval low measurement values ​​during the detection period is calculated by ratio with the total operation time of the DC motor during the detection period to obtain the recognition interval low condition value;

[0017] And through analysis, the fault summary table value is obtained, the low-condition value and the fault summary table value are numerically calculated to obtain the motor safety analysis value, and the motor safety analysis value is numerically compared with the preset motor safety analysis threshold. If the motor safety analysis value exceeds the preset motor safety analysis threshold, a motor safety abnormality signal is generated; if the motor safety analysis value does not exceed the preset motor safety analysis threshold, a motor safety qualified signal is generated.

[0018] Further, the method for analyzing and obtaining the fault comprehensive table value is as follows:

[0019] The fault final analysis value is obtained by calculating the ratio of the fault final condition value of the target fault i and the corresponding preset fault final condition threshold value. A set of preset fault weight values ​​is set in advance for each type of fault. The fault final analysis value of the target fault i is multiplied by the corresponding preset fault weight value to obtain the fault risk measurement value. The fault risk measurement values ​​of all types of faults occurring in the DC motor during the detection period are summed up to obtain the fault comprehensive table value.

[0020] Further, the motor fault identification output module is communicatively connected to the motor hidden danger decision module. During the operation of the DC motor, if the motor fault identification output module does not detect the fault of the DC motor, a hidden danger analysis signal is generated and sent to the motor hidden danger decision module;

[0021] When the motor hidden danger decision module receives the hidden danger analysis signal, it performs auxiliary analysis on the operation hidden danger of the DC motor, generates a hidden danger warning signal or a no hidden danger signal through analysis, and sends the hidden danger warning signal or the no hidden danger signal to the supervision terminal. When the supervision terminal receives the hidden danger warning signal, it issues a corresponding warning.

[0022] Furthermore, the specific analysis process of the motor hidden danger decision module is as follows:

[0023] The parts of the DC motor that need to be lubricated are obtained, and the corresponding parts that need to be lubricated are marked as monitoring objects u, where u is a natural number greater than 1; the time when the monitoring object u was lubricated last time is collected and marked as the adjacent coating time, and the interval between the current time and the adjacent coating time is marked as the coating interval time;

[0024] The smearing interval time is numerically compared with the corresponding preset smearing interval time threshold. If the smearing interval time exceeds the corresponding preset smearing interval time threshold, the monitoring object u is marked as a warning object; if the smearing interval time does not exceed the corresponding preset smearing interval time threshold, the smearing urgency value of the monitoring object u is obtained through analysis, and the smearing urgency value is numerically compared with the corresponding preset smearing urgency threshold. If the smearing urgency value exceeds the corresponding preset smearing urgency threshold, the monitoring object u is marked as a warning object;

[0025] If there are warning objects in the DC motor, a hidden danger warning signal is generated; if there are no warning objects in the DC motor, a ventilation and heat dissipation decision analysis is performed.

[0026] Furthermore, the specific analysis process of obtaining the smear urgency value of the monitoring object u through analysis is as follows:

[0027] The humidity of the environment where the monitored object u is located is collected, and the difference between the humidity and the median of the set standard humidity range is calculated and the absolute value is taken to obtain the humidity value of the part, and the temperature of the monitored object u and the dust concentration of the environment where it is located are collected and marked as the temperature value of the part and the dust value of the part respectively;

[0028] The lubrication influence value of the part is obtained by numerically calculating the wet condition value, the temperature condition value and the gray condition value of the part, and the lubrication influence value of the part is numerically compared with the preset lubrication influence threshold of the part. If the lubrication influence value of the part exceeds the preset lubrication influence threshold of the part, it is judged that the monitored object u is in a lubrication-poor influence state;

[0029] The total duration of the monitoring object u in the lubrication-poor state within the coating gap time is obtained and marked as the lubrication-poor time value, and the average of all part lubrication impact values ​​within the coating gap time is calculated to obtain the part lubrication assessment value, and the coating urgency value is obtained by numerically calculating the coating gap time, lubrication-poor time value and part lubrication assessment value of the monitoring object u.

[0030] Furthermore, the specific analysis process of ventilation and heat dissipation decision analysis is as follows:

[0031] The temperatures of several positions inside the DC motor are obtained and their average is calculated to obtain the internal temperature value of the motor. The air inlet speed and air inlet temperature of the DC motor during ventilation and heat dissipation are collected and marked as the air inlet speed table value and the air inlet temperature table value respectively. The air inlet volume of the DC motor per unit time is collected and marked as the ventilation volume table value.

[0032] The ventilation and heat dissipation decision value is obtained by numerically calculating the motor internal temperature value, the inlet air speed meter value, the inlet air temperature meter value and the ventilation volume meter value, and the ventilation and heat dissipation decision value is numerically compared with the preset ventilation and heat dissipation decision value range. If the ventilation and heat dissipation decision value is within the preset ventilation and heat dissipation decision value range, a no hidden danger signal is generated; if the ventilation and heat dissipation decision value is not within the preset ventilation and heat dissipation decision value range, a hidden danger warning signal is generated.

[0033] Furthermore, the specific analysis process of the motor availability analysis module is as follows:

[0034] The scrapping date of the DC motor is obtained. If the scrapping date has been exceeded, a low availability signal is generated; if the scrapping date has not been exceeded, the interval between the current date and the scrapping date is marked as the scrapping interval value, and the total operating time of the DC motor in the historical stage is collected and marked as the motor operating time value;

[0035] And in the corresponding operation process of the DC motor, the average load, duration, average operating temperature and average vibration amplitude of the DC motor are collected, and the average load, duration, average operating temperature and average vibration amplitude are numerically calculated to obtain the motor operation value; the motor operation value is numerically compared with a preset motor operation threshold value, and if the motor operation value exceeds the preset motor operation threshold value, the corresponding operation process of the DC motor is marked as a damage process;

[0036] The number of damage processes corresponding to the DC motor in the historical stage is obtained and marked as a damage detection value. The motor availability coefficient is obtained by numerically calculating the scrap interval value, the motor operation time value and the damage detection value. The motor availability coefficient is numerically compared with the preset motor availability coefficient threshold. If the motor availability coefficient exceeds the preset motor availability coefficient threshold, a low availability signal is generated; if the motor availability coefficient does not exceed the preset motor availability coefficient threshold, a high availability signal is generated.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. In the present invention, the motor fault identification output module is used to analyze whether the DC motor has a fault. If it is determined that the DC motor has a fault, the supervisor is reminded to take corresponding control measures for the DC motor in a timely manner as needed, and the motor safety analysis module is used to analyze the operating safety of the DC motor during the detection period. When the motor safety warning signal is generated, the motor availability analysis module is used to analyze the availability of the DC motor, which is conducive to the supervisor's reasonable disposal of the DC motor and subsequent supervision plan planning, reducing the management difficulty of the supervisor, and ensuring the safe and stable operation of the DC motor;

[0039] 2. In the present invention, when the motor fault identification output module does not detect the fault of the DC motor, the motor hidden danger decision module performs auxiliary analysis on the operation hidden danger of the DC motor, and generates a hidden danger warning signal or a no hidden danger signal through analysis. When the hidden danger warning signal is generated, the supervisor is reminded to take corresponding improvement measures, thereby further ensuring the safe and stable operation of the DC motor, with a high degree of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0041] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0042] Figure 2 This is a system block diagram of Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1: Figure 1 As shown, the DC motor operation fault detection system based on artificial intelligence proposed in the present invention includes a motor monitoring transmission module, a motor fault identification output module, a motor safety analysis module, a motor availability analysis module and a supervision terminal;

[0045] The motor monitoring transmission module monitors the operation of the DC motor, collects various operating data of the DC motor (including current, voltage, speed, etc.) and sends them to the motor fault identification output module;

[0046] The motor fault identification output module is based on an artificial intelligence fault detection model (using a deep learning algorithm, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), to train and learn the motor's operating data and establish a motor fault detection model. The model can automatically identify the motor's operating status, determine whether there is a fault, and give the fault type). The module analyzes the motor's operating data to determine whether the DC motor has a fault. If the DC motor is judged to have a fault, a fault warning signal is generated. When the fault warning signal is generated, the supervision terminal issues a corresponding warning, which makes it convenient for supervisors to grasp the DC motor's operating fault information in detail and make corresponding control measures for the DC motor in a timely manner as needed, thereby ensuring the safe and stable operation of the DC motor.

[0047] The motor safety analysis module is used to set a detection period of L1, preferably, the detection period is seven days; the operation safety of the DC motor during the detection period is analyzed, and a motor safety qualified signal or a motor safety warning signal is generated through analysis. When the motor safety warning signal is generated, the supervision terminal issues a corresponding warning, and the use risk of the DC motor can be reasonably analyzed and comprehensively evaluated and output, so as to remind the supervisory personnel to strengthen the subsequent supervision of the DC motor in time and reduce the subsequent use risk of the DC motor; the specific analysis process of the motor safety analysis module is as follows:

[0048] All faults occurring in the DC motor during the detection period are obtained, all faults are classified, and the corresponding type of fault is marked as a target fault i, where i is a natural number greater than 1; the number of times the target fault i occurs in the DC motor during the detection period is collected and marked as the initial fault value, and the ratio of the initial fault value to the total running time of the DC motor during the detection period is calculated to obtain the final fault value;

[0049] The fault final condition value is numerically compared with the corresponding preset fault final condition threshold. If the fault final condition value exceeds the preset fault final condition threshold, it indicates that the occurrence frequency of the target fault i during the detection period is high, and the target fault i is marked as a frequent fault; if the DC motor has frequent faults during the detection period, it indicates that the use risk of the DC motor during the detection period is relatively high, and a motor safety abnormality signal is generated.

[0050] Furthermore, if there are no frequent faults in the DC motor during the detection period, the occurrence time of all faults in the DC motor during the detection period is obtained, the occurrence time of the corresponding fault is marked as the identification time, and the interval between two adjacent groups of identification time is marked as the identification interval time;

[0051] Compare the inter-recognition time with the preset inter-recognition time threshold, count the number of inter-recognition time that does not exceed the preset inter-recognition time threshold during the detection period and mark it as the inter-recognition low measurement value, and calculate the ratio of the number of inter-recognition low measurement values ​​during the detection period to the total operation time of the DC motor during the detection period to obtain the inter-recognition low condition value; wherein, the larger the value of the inter-recognition low condition value is, the more unstable the operation process of the DC motor during the detection period is;

[0052] The fault final analysis value is obtained by calculating the ratio of the fault final condition value of the target fault i to the corresponding preset fault final condition threshold; each type of fault is set in advance to correspond to a set of preset fault weight values ​​greater than zero, and the greater the risk of the corresponding type of fault to the DC motor, the greater the value of the preset fault weight value adapted to it;

[0053] The fault final analysis value of the target fault i is multiplied by the corresponding preset fault weight value to obtain the fault risk measurement value, and the fault risk measurement values ​​of all types of faults occurring in the DC motor during the detection period are summed up to obtain the fault comprehensive table value;

[0054] The motor safety analysis value TL is obtained by numerically calculating the low-condition value TS and the fault summary table value TP through the formula TL=sy1*TS+sy2*TP; wherein sy1 and sy2 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the motor safety analysis value TL is, the worse the overall operating condition of the DC motor during the detection period is, and the more it is necessary to strengthen the operation supervision of the DC motor in the subsequent period;

[0055] The motor safety analysis value is numerically compared with the preset motor safety analysis threshold. If the motor safety analysis value exceeds the preset motor safety analysis threshold, it indicates that the operating condition of the DC motor during the detection period is generally poor, and a motor safety abnormality signal is generated; if the motor safety analysis value does not exceed the preset motor safety analysis threshold, it indicates that the operating condition of the DC motor during the detection period is generally good, and a motor safety qualified signal is generated.

[0056] The motor safety analysis module sends the motor safety warning signal to the motor availability analysis module. When the motor availability analysis module receives the motor safety warning signal, it performs availability analysis on the DC motor, generates a low availability signal or a high availability signal through analysis, and causes the supervision terminal to issue a corresponding warning when a low availability signal is generated. When the supervisor receives the warning of the low availability signal, the DC motor is scrapped, which reduces the subsequent safety hazards in use, is conducive to the supervisor's reasonable disposal of the DC motor, and reduces the management difficulty of the supervisor. The specific analysis process of the motor availability analysis module is as follows:

[0057] The scrapping date of the DC motor is obtained. If the scrapping date has been exceeded, indicating that the DC motor is tending to be scrapped, a low availability signal is generated; if the scrapping date has not been exceeded, the interval between the current date and the scrapping date is marked as the scrapping interval value, and the total operating time of the DC motor in the historical stage is collected and marked as the motor operating time value;

[0058] And during the corresponding operation of the DC motor, the average load, duration, average operating temperature and average vibration amplitude of the DC motor are collected;

[0059] The motor operation value LM is obtained by numerically calculating the average load WX, the duration WF, the average operating temperature WK and the average vibration amplitude WS through the formula LM=(a1*WX+a2*WF+a3*WK+a4*WS) / 4; wherein a1, a2, a3, and a4 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the motor operation value LM is, the greater the potential damage to the DC motor caused by the corresponding operation process;

[0060] The motor operation value LM is numerically compared with the preset motor operation threshold. If the motor operation value LM exceeds the preset motor operation threshold, it indicates that the corresponding operation process has caused great potential damage to the DC motor, and the corresponding operation process of the DC motor is marked as a damage process; the number of damage processes corresponding to the DC motor in the historical stage is obtained and marked as a damage detection value;

[0061] The motor availability coefficient YK is obtained by numerically calculating the scrap interval value YG, the motor operation time value YL and the damage detection value YM through the formula YK=(hm2*YL+hm3*YM) / (hm1*YG+1); wherein hm1, hm2 and hm3 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the motor availability coefficient YK is, the more the DC motor cannot be used any more and the more it tends to be scrapped;

[0062] The motor availability coefficient YK is numerically compared with the preset motor availability coefficient threshold. If the motor availability coefficient exceeds the preset motor availability coefficient threshold, it indicates that the DC motor tends to be scrapped, and a low availability signal is generated; if the motor availability coefficient YK does not exceed the preset motor availability coefficient threshold, it indicates that the DC motor can still be used, and a high availability signal is generated.

[0063] Embodiment 2: Figure 2 As shown, the difference between this embodiment and the first embodiment is that the motor fault identification output module is communicatively connected to the motor hidden danger decision module. During the operation of the DC motor, if the motor fault identification output module does not detect the fault of the DC motor, a hidden danger analysis signal is generated and sent to the motor hidden danger decision module;

[0064] When the motor hidden danger decision module receives the hidden danger analysis signal, it performs auxiliary analysis on the operation hidden danger of the DC motor, generates a hidden danger warning signal or a no hidden danger signal through analysis, and sends the hidden danger warning signal or the no hidden danger signal to the supervision terminal. When the supervision terminal receives the hidden danger warning signal, it issues a corresponding warning. When the supervisor receives the warning, he takes corresponding improvement measures, thereby further ensuring the safe and stable operation of the DC motor. The specific analysis process of the motor hidden danger decision module is as follows:

[0065] The parts that need to be lubricated in the DC motor are obtained, and the corresponding parts that need to be lubricated (mainly the transmission parts inside the motor) are marked as monitoring objects u, where u is a natural number greater than 1; the time when the monitoring object u was lubricated last time is collected and marked as the adjacent coating time, and the interval between the current time and the adjacent coating time is marked as the coating interval time;

[0066] Compare the coating interval time with the corresponding preset coating interval time threshold. If the coating interval time exceeds the corresponding preset coating interval time threshold, it indicates that lubricant needs to be applied to the monitored object u, and the monitored object u is marked as a warning object.

[0067] If the coating interval does not exceed the corresponding preset coating interval threshold, the humidity of the environment where the monitored object u is located is collected, and the difference between the humidity and the median of the set standard humidity range is calculated and the absolute value is taken to obtain the part humidity value, and the temperature of the monitored object u and the dust concentration of the environment are collected and marked as the part temperature value and the part gray value respectively;

[0068] By formula The part lubrication influence value RLu is obtained by numerically calculating the part wetness value RYu, the part temperature value RMu and the part gray value RXu; wherein up1, up2 and up3 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the part lubrication influence value RLu is, the greater the adverse effect of the environmental conditions of the monitored object u on its surface lubrication condition is;

[0069] The part lubrication influence value RLu is numerically compared with the preset part lubrication influence threshold. If the part lubrication influence value RLu exceeds the preset part lubrication influence threshold, it indicates that the environmental conditions of the monitored object u have a greater adverse effect on its surface lubrication condition, and the monitored object u is judged to be in a state of poor lubrication influence;

[0070] The total time duration of the monitored object u in the lubrication-impacted state within the coating gap time is obtained and marked as the lubrication-impacted time value, and the lubrication-impacted values ​​of all parts within the coating gap time are averaged to obtain the part lubrication assessment value;

[0071] The coating interval time QSu, lubrication inferior time value QRu and part lubrication assessment value QPu of the monitoring object u are numerically calculated by the formula QMu=(wg1*QSu+wg2*QRu) / 2+wg3*QPu to obtain the coating urgency value QMu; wherein wg1, wg2 and wg3 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the coating urgency value QMu is, the more lubricating oil needs to be coated on the surface of the monitoring object u at present;

[0072] The smearing urgency value QMu is numerically compared with the corresponding preset smearing urgency threshold value. If the smearing urgency value QMu exceeds the corresponding preset smearing urgency threshold value, it indicates that lubricating oil needs to be smeared on the surface of the monitoring object u, and the monitoring object u is marked as a warning object; if there is a warning object in the DC motor, it indicates that the DC motor currently has a safety hazard in operation, and a hidden danger warning signal is generated;

[0073] If there is no warning object in the DC motor, a ventilation and heat dissipation decision analysis is performed, specifically: the temperatures of several positions inside the DC motor are obtained and the average is calculated to obtain the internal temperature value of the motor, and the air inlet speed and air inlet temperature of the DC motor during ventilation and heat dissipation are collected and marked as the air inlet speed table value and the air inlet temperature table value respectively, and the air intake volume of the DC motor per unit time is collected and marked as the ventilation volume table value;

[0074] By formula The motor internal temperature value FY, the inlet air speed meter value FN, the inlet air temperature meter value FW and the ventilation volume meter value FK are numerically calculated to obtain the ventilation and heat dissipation decision value FX; wherein ew1, ew2, ew3 and ew4 are preset proportional coefficients with values ​​greater than zero, and when the value of the ventilation and heat dissipation decision value FX is too small, it indicates that the current heat dissipation effect of the DC motor is poor, and when the value of the ventilation and heat dissipation decision value FX is too large, it indicates that there is excessive heat dissipation, which increases unnecessary operating energy consumption;

[0075] The ventilation and heat dissipation decision value FX is numerically compared with the preset ventilation and heat dissipation decision value range. If the ventilation and heat dissipation decision value FX is within the preset ventilation and heat dissipation decision value range, it indicates that the current heat dissipation performance of the DC motor is good, and a no hidden danger signal is generated; if the ventilation and heat dissipation decision value FX is not within the preset ventilation and heat dissipation decision value range, it indicates that the current heat dissipation performance of the DC motor is poor, and a hidden danger warning signal is generated.

[0076] The working principle of the present invention is as follows: when in use, the operation of the DC motor is monitored through the motor monitoring transmission module, and various operation data of the DC motor are sent to the motor fault identification output module. The motor fault identification output module analyzes various operation data of the motor based on the fault detection model of artificial intelligence to determine whether the DC motor has a fault. If it is determined that the DC motor has a fault, the supervisor is reminded to take corresponding control measures for the DC motor in a timely manner as needed to ensure the safe and stable operation of the DC motor. The operation safety of the DC motor during the detection period is analyzed through the motor safety analysis module to generate a motor safety qualification signal or a motor safety early warning signal. When the motor safety early warning signal is generated, the DC motor is analyzed for availability through the motor availability analysis module to generate a low availability signal or a high availability signal, which is conducive to the supervisor's reasonable disposal of the DC motor and subsequent supervision plan planning, reduces the management difficulty of the supervisor, and has a high degree of intelligence.

[0077] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. The DC motor operation fault detection system based on artificial intelligence is characterized by: It includes a motor monitoring transmission module, a motor fault identification output module, a motor safety analysis module, a motor availability analysis module and a supervision terminal; the motor monitoring transmission module monitors the operation of the DC motor, collects various operation data of the DC motor and sends them to the motor fault identification output module; The motor fault identification output module analyzes various operating data of the motor based on the fault detection model of artificial intelligence to determine whether the DC motor has a fault. If it is determined that the DC motor has a fault, a fault warning signal is generated, and when the fault warning signal is generated, the monitoring terminal issues a corresponding warning; The motor safety analysis module analyzes the operation safety of the DC motor during the detection period, generates a motor safety qualification signal or a motor safety warning signal through the analysis, and sends the motor safety warning signal to the motor availability analysis module; When the motor availability analysis module receives the motor safety warning signal, it performs availability analysis on the DC motor and generates a low availability signal or a high availability signal through analysis. When the motor safety warning signal or the low availability signal is generated, the monitoring terminal issues a corresponding warning.

2. The artificial intelligence-based DC motor operation fault detection system according to claim 1 is characterized in that: The specific analysis process of the motor safety analysis module is as follows: Obtain all faults that occur in the DC motor during the detection period, classify all faults, and mark the corresponding type of fault as target fault i, where i is a natural number greater than 1; If the fault final condition value exceeds the preset fault final condition threshold, the target fault i is marked as a frequent fault; if the DC motor has frequent faults during the detection period, a motor safety abnormality signal is generated.

3. The artificial intelligence-based DC motor operation fault detection system according to claim 2 is characterized in that: If there is no frequent fault in the DC motor during the detection period, the fault comprehensive table value is obtained through analysis, and the low-condition value and the fault comprehensive table value are numerically calculated to obtain the motor safety analysis value. If the motor safety analysis value exceeds the preset motor safety analysis threshold, a motor safety abnormality signal is generated; If the motor safety analysis value does not exceed the preset motor safety analysis threshold, a motor safety qualified signal is generated.

4. The artificial intelligence-based DC motor operation fault detection system according to claim 3 is characterized in that: The analysis and acquisition method of the fault comprehensive table value is as follows: The fault final analysis value is obtained by calculating the ratio of the fault final condition value of the target fault i and the corresponding preset fault final condition threshold value, the fault final analysis value of the target fault i is multiplied by the corresponding preset fault weight value to obtain the fault risk measurement value, and the fault risk measurement values ​​of all types of faults occurring in the DC motor during the detection period are summed up to obtain the fault summary table value.

5. The artificial intelligence-based DC motor operation fault detection system according to claim 1 is characterized in that: The motor fault identification output module is communicatively connected to the motor hidden danger decision module. If the motor fault identification output module does not detect the fault of the DC motor, the motor hidden danger decision module will perform auxiliary analysis on the operation hidden danger of the DC motor, generate a hidden danger warning signal or a no hidden danger signal through the analysis, and send the hidden danger warning signal or the no hidden danger signal to the supervision terminal.

6. The artificial intelligence-based DC motor operation fault detection system according to claim 5 is characterized in that: The specific analysis process of the motor hidden danger decision module is as follows: The parts that need to be lubricated in the DC motor are obtained, and the corresponding parts that need to be lubricated are marked as monitoring objects u, where u is a natural number greater than 1; if the coating interval time exceeds the corresponding preset coating interval time threshold, the monitoring object u is marked as a warning object; if the coating interval time does not exceed the corresponding preset coating interval time threshold, the coating urgency value of the monitoring object u is obtained through analysis, and if the coating urgency value exceeds the corresponding preset coating urgency threshold, the monitoring object u is marked as a warning object; If there is a warning object in the DC motor, a hidden danger warning signal is generated; If there is no warning object in the DC motor, ventilation and heat dissipation decision analysis is performed.

7. The artificial intelligence-based DC motor operation fault detection system according to claim 6 is characterized in that: The specific analysis process of obtaining the smear urgency value of the monitoring object u through analysis is as follows: The total duration of the monitoring object u in the lubrication-poor state within the coating gap time is obtained and marked as the lubrication-poor time value, and the average of all part lubrication impact values ​​within the coating gap time is calculated to obtain the part lubrication assessment value, and the coating urgency value is obtained by numerically calculating the coating gap time, lubrication-poor time value and part lubrication assessment value of the monitoring object u.

8. The artificial intelligence-based DC motor operation fault detection system according to claim 6 is characterized in that: The specific analysis process of ventilation and heat dissipation decision analysis is as follows: The ventilation and heat dissipation decision value is obtained by numerically calculating the motor internal temperature value, the inlet air speed meter value, the inlet air temperature meter value and the ventilation volume meter value. If the ventilation and heat dissipation decision value is within the preset ventilation and heat dissipation decision value range, a no hidden danger signal is generated; if the ventilation and heat dissipation decision value is not within the preset ventilation and heat dissipation decision value range, a hidden danger warning signal is generated.

Images