AC motor starting control method and device

Abstract

The present invention provides a method and device for starting and controlling an AC motor. The method includes: training a GAN network by obtaining multiple groups of signal data and the corresponding start commands for each group of signal data, and analyzing and processing real-time signal data using the trained motor control model network model, so as to obtain real-time start commands, and controlling the motor switch according to the real-time start commands. The beneficial effects of the present invention are as follows: realizing the automatic generation of real-time start commands, without manual operation, generating corresponding start commands according to the detected data, improving work efficiency, and realizing intelligent control.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and particularly to a method and device for controlling the starting of an AC motor. Background Art

[0002] Existing AC motor control circuits are generally controlled by operators, which results in high labor intensity and unsafe operation for the operators. If program control is set to turn off and start, it is impossible to intelligently control the AC motor according to the actual situation.

[0003] Therefore, there are defects in the prior art and improvement is needed. Summary of the Invention

[0004] The main object of the present invention is to provide a method and device for controlling the starting of an AC motor, aiming to solve the problem that the AC motor cannot be intelligently controlled according to the actual situation.

[0005] The present invention provides a method for controlling the starting of an AC motor, which is implemented through a starting control circuit. The starting control circuit includes a power supply, a CPU, a motor switch, a motor, and a plurality of detection units. The motor switch is controlled by the CPU and connected to the CPU. Each detection unit is connected to the CPU. The power supply, the motor switch, and the motor form a circuit. The method for controlling the starting of the AC motor includes:

[0006] Obtain multiple sets of signal data and the starting instructions corresponding to each set of signal data; wherein, a set of signal data includes a first signal of the motor voltage and a second signal of the input power supply;

[0007] Preprocess each of the first signals and the second signals to obtain a first target signal and a second target signal;

[0008] Input each set of the first target signals and the starting instructions into the generation model in the GAN network model, and input the second target signals and the starting instructions into the discriminant model in the GAN network model for training to obtain a trained motor control model network model;

[0009] Obtain real-time first signals and real-time second signals through the detection unit and convert them into real-time first target signals and real-time second target signals;

[0010] Input the real-time first target signals and the real-time second target signals into the motor control model network model to obtain real-time starting instructions;

[0011] Control the motor switch according to the real-time starting instructions.

[0012] Further, the step of inputting each group of the first target signals and the start instruction into the generation model in the GAN network model, and inputting the second target signals and the start instruction into the discriminant model in the GAN network model for training to obtain a trained motor control model network model includes:

[0013] Input the first target signal into the generation model to obtain the best prediction value, input the start instruction into the generation model, and perform initial training on the generation model through the formula to obtain the temporarily predicted value after training and the first intermediate model, and input the second target signal and the start instruction into the discriminant model, and perform initial training on the discriminant model through the formula to obtain the second intermediate model; where , , represents the parameter set of the generation model, represents the parameter set of the discriminant model, is the best prediction value;

[0014] According to the formula perform secondary training on the first intermediate model and the second intermediate model, and after the training is completed, obtain the motor control model network model; where means taking the minimum value of and the maximum value of on the premise of satisfying the above formula.

[0015] Further, the AC motor starting control circuit further includes: the motor switch is a thyristor of the motor switch, the first terminal Z2, the second terminal V1, the third terminal V2, and the fourth terminal Z1 of the thyristor of the motor switch are connected to the motor, a winding, and a capacitor; the capacitor includes a running capacitor CR and a starting capacitor CS, the running capacitor CR is connected to the winding, and both ends of the starting capacitor CS are respectively connected to the third terminal V2 and the fourth terminal Z1; both ends of the thyristor are respectively connected to the second terminal V1 and the third terminal V2; the second terminal V1 is used to collect the signal of the input power supply and send the sampled signal to the CPU, the fourth terminal is used to collect the signal of the motor voltage and send the sampled signal to the CPU, and the CPU controls the opening and closing of the thyristor through a driving module.

[0016] Further, the step of respectively preprocessing each of the first signals and the second signals to obtain the first target signal and the second target signal includes:

[0017] Convert the first target signal according to a preset first conversion method, and convert the second signal into a second target signal according to a preset second conversion method; wherein, the first target signal and the second target signal have the same dimension.

[0018] Further, after the step of obtaining the real-time first signal and the real-time second signal by the detection unit, the method further includes:

[0019] Determine whether both the real-time first signal and the real-time second signal are within a preset range;

[0020] If both are within the preset range, execute the step of converting into a real-time first target signal and a real-time second target signal;

[0021] If not within the preset range, control the motor switch to turn off.

[0022] The present invention also provides an AC motor starting control device, which is realized by a starting control circuit. The starting control circuit includes a power supply, a CPU, a motor switch, a motor, and a plurality of detection units. The motor switch is controlled by the CPU and connected, and each detection unit is connected to the CPU. The power supply, the motor switch, and the motor form a loop. The AC motor starting control device includes:

[0023] An acquisition module, configured to acquire multiple groups of signal data and the starting instructions corresponding to each group of signal data; wherein, a group of signal data includes a first signal of the motor voltage and a second signal of the input power supply;

[0024] A preprocessing module, configured to preprocess each of the first signal and the second signal respectively to obtain a first target signal and a second target signal;

[0025] A first input module, configured to input each group of the first target signals and the starting instructions into a generation model in a GAN network model, and input the second target signal and the starting instructions into a discriminant model in the GAN network model for training to obtain a trained motor control model network model;

[0026] A conversion module, configured to obtain a real-time first signal and a real-time second signal through a detection unit, and convert them into a real-time first target signal and a real-time second target signal;

[0027] A second input module, configured to input the real-time first target signal and the real-time second target signal into the motor control model network model to obtain a real-time starting instruction;

[0028] A control module, configured to control the motor switch according to the real-time starting instruction.

[0029] Further, the first input module includes:

[0030] An input sub-module for inputting the first target signal into the generation model to obtain an optimal prediction value, inputting the start instruction into the generation model, and initially training the generation model through the formula to obtain a temporarily predicted value after training and a first intermediate model, and inputting the second target signal and the start instruction into the discriminant model, and initially training the discriminant model through the formula to obtain a second intermediate model; where , , represents the parameter set of the generation model, represents the parameter set of the discriminant model, is the optimal prediction value;

[0031] A training sub-module for secondarily training the first intermediate model and the second intermediate model according to the formula to obtain a motor control model network model after training; where represents taking the minimum value of and the maximum value of on the premise of satisfying the above formula.

[0032] Further, the AC motor starting control circuit further includes: the motor switch is a thyristor of the motor switch, and the thyristor of the motor switch is connected to the first terminal Z2, the second terminal V1, the third terminal V2, and the fourth terminal Z1 of the motor, a winding, and a capacitor; the capacitor includes a running capacitor CR and a starting capacitor CS, the running capacitor CR is connected to the winding, and both ends of the starting capacitor CS are respectively connected to the third terminal V2 and the fourth terminal Z1; both ends of the thyristor are respectively connected to the second terminal V1 and the third terminal V2; the second terminal V1 is used for collecting the signal of the input power supply and sending the sampled signal to the CPU, the fourth terminal is used for collecting the signal of the motor voltage and sending the sampled signal to the CPU, and the CPU controls the opening and closing of the thyristor through a driving module.

[0033] Further, the preprocessing module includes:

[0034] A conversion sub-module for converting the first target signal into a first target signal according to a preset first conversion method, and converting the second signal into a second target signal according to a preset second conversion method; where the dimensions of the first target signal and the second target signal are the same.

[0035] Furthermore, the AC motor starting control device further includes:

[0036] A judgment module, configured to judge whether both the real-time first signal and the real-time second signal are within a preset range;

[0037] An execution module, configured to, if both are within the preset range, execute the step of converting to a real-time first target signal and a real-time second target signal;

[0038] A control module, configured to, if not within the preset range, control the motor switch to turn off.

[0039] Advantages of the present invention: By obtaining multiple groups of signal data and the corresponding start instructions for each group of signal data to train the GAN network, and using the trained motor control model network model to analyze and process the real-time signal data, the real-time start instruction can be obtained, and the motor switch is controlled according to the real-time start instruction, thereby realizing the automatic generation of the real-time start instruction, without manual operation, and the corresponding start instruction can be generated according to the detected data, improving the work efficiency and realizing intelligent control. Description of the Drawings

[0040] Figure 1 is a schematic flowchart of a method for controlling the start of an AC motor according to an embodiment of the present invention;

[0041] Figure 2 is a schematic block diagram of the structure of an AC motor starting control device according to an embodiment of the present invention;

[0042] Figure 3 is a circuit diagram of an AC motor starting control according to an embodiment of the present invention;

[0043] Figure 4 is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0044] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a certain specific posture (as shown in the attached drawings). If the specific posture changes, the directional indications will also change accordingly. The connection described herein can be a direct connection or an indirect connection.

[0047] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0048] In addition, in the present invention, descriptions such as "first" and "second" are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the fact that those skilled in the art can implement them. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0049] Referring to Figure 1 , the present invention proposes an AC motor starting control method, which is implemented through a starting control circuit. The starting control circuit includes a power supply, a CPU, a motor switch, a motor, and multiple detection units. The motor switch is controlled by the CPU and connected, and each detection unit is connected to the CPU. The power supply, the motor switch, and the motor form a loop. The AC motor starting control method includes:

[0050] S1: Obtain multiple groups of signal data and the starting instructions corresponding to each group of signal data; wherein, a group of signal data includes a first signal of the motor voltage and a second signal of the input power supply;

[0051] S2: Perform preprocessing on each of the first signals and the second signals respectively to obtain a first target signal and a second target signal;

[0052] S3: Input each group of the first target signals and the starting instructions into the generation model in the GAN network model, and input the second target signals and the starting instructions into the discriminant model in the GAN network model for training to obtain a trained motor control model network model;

[0053] S4: Obtain real-time first signals and real-time second signals through the detection unit and convert them into real-time first target signals and real-time second target signals;

[0054] S5: Input the real-time first target signal and the real-time second target signal into the motor control model network model to obtain a real-time start command.

[0055] S6: Control the motor switch according to the real-time start command.

[0056] As described in step S1 above, obtain multiple groups of signal data and the corresponding start commands. Specifically, the acquisition method can be to obtain from historical data, that is, it can be recorded in advance, and then these data are manually uploaded to achieve the acquisition of the corresponding data.

[0057] As described in step S2 above, preprocess each of the first signal and the second signal to obtain a first target signal and a second target signal. Among them, the preprocessing can be to remove some irrelevant data, reduce noise, remove duplicates, etc. The most important thing is to convert the corresponding data into a preset format for subsequent processing.

[0058] As described in step S3 above, input each group of the first target signals and the start commands into the generation model in the GAN network model, and input the second target signals and the start commands into the discriminant model in the GAN network model for training to obtain a trained motor control model network model. Among them, the generation model and the discriminant model are cross-trained. The cross-training method is that the generation model needs to be corrected according to the output result of the discriminant model, and the discriminant model needs to be corrected according to the output result of the generation model. Specifically, when the data are respectively input into the generation model and the discriminant model, corresponding output results can be obtained. This output result is generally a specific value. Then the generation model corrects its own output result according to the output result of the discriminant model. Similarly, the discriminant model is corrected according to the output result of the generation model, so as to perform cross-training to obtain a trained motor control model network model.

[0059] As described in steps S4 - S6 above, obtain the real-time first signal and the real-time second signal through the detection unit and convert them into the real-time first target signal and the real-time second target signal. Input the real-time first target signal and the real-time second target signal into the motor control model network model to obtain a real-time start command, and control the motor switch according to the real-time start command. Thus, the automatic generation of the real-time start command is realized, without manual operation, and the corresponding start command can be generated according to the detected data.

[0060] In one embodiment, step S3 of inputting each group of the first target signals and the start instruction into the generation model in the GAN network model, and inputting the second target signal and the start instruction into the discriminant model in the GAN network model for training to obtain the trained motor control model network model includes:

[0061] S301: Input the first target signal into the generation model to obtain the optimal predicted value, input the start instruction into the generation model, and perform initial training on the generation model through the formula to obtain the temporarily predicted value after training and the first intermediate model, and input the second target signal and the start instruction into the discriminant model, and perform initial training on the discriminant model through the formula to obtain the second intermediate model; where , , represents the parameter set of the generation model, represents the parameter set of the discriminant model, is the optimal predicted value;

[0062] S302: Perform secondary training on the first intermediate model and the second intermediate model according to the formula After the training is completed, the motor control model network model is obtained; where represents taking the minimum value of and the maximum value of on the premise of satisfying the above formula.

[0063] As described in the above steps S301 - S302, perform initial training on the generation model through the formula and perform initial training on the discriminant model through the formula , then use the stochastic gradient descent method for training, perform training on the next sample after the current sample training is completed, and update the parameters in the generation model and the discriminant model after each training is completed. It should be noted that each sample needs to be trained with the above three formulas, that is, during the training process of a group of samples, the parameters need to be updated twice, so that the motor control model network model is finally obtained after the training is completed.

[0064] Refer to Figure 2, in one embodiment, the AC motor starting control circuit further includes: the motor switch is the motor switch thyristor, the first terminal Z2, the second terminal V1, the third terminal V2, and the fourth terminal Z1 of the motor switch thyristor connected to the motor, a winding, and a capacitor; the capacitor includes a running capacitor CR and a starting capacitor CS, the running capacitor CR is connected to the winding, and both ends of the starting capacitor CS are respectively connected to the third terminal V2 and the fourth terminal Z1; both ends of the thyristor are respectively connected to the second terminal V1 and the third terminal V2; the second terminal V1 is used to collect the signal of the input power supply and send the sampled signal to the CPU, the fourth terminal is used to collect the signal of the motor voltage and send the sampled signal to the CPU, and the CPU controls the opening and closing of the thyristor through a driving module.

[0065] The control switch is a manual switch:

[0066] When pressing the up key, the first winding M1 is the main winding, and the second winding M2 is the auxiliary winding. The running capacitor CR is connected between the first winding M1 and the second winding M2. One end of the running capacitor CR is connected to the second terminal V1, and the other end is connected to the fourth terminal Z1. The fourth terminal Z1 is connected to the starting capacitor CS, and the other end of the starting capacitor CS is connected to the third terminal V2. The other end of the third terminal V2 is connected to the thyristor, and the other end of the thyristor is connected to the second terminal V1. The second terminal V1 is connected to the running capacitor CR, thus forming a set of interlocking switches.

[0067] When pressing the down key, the second winding M2 is the main winding, and the first winding M1 is the auxiliary winding. The second winding M2 is connected to the second terminal V1, the first winding M1 is connected to the fourth terminal Z1, the fourth terminal Z1 is connected to the starting capacitor CS, the other end of the starting capacitor CS is connected to the third terminal V2, the other end of the third terminal V2 is connected to the thyristor, and the other end of the thyristor is connected to the second terminal V1, thus forming another set of interlocking switches.

[0068] Working principle: After the power supply is connected, press the up and down keys to control the forward and reverse operation. When the key pressing is completed, the sampled signal and the signal triggering the third terminal V2 are transmitted to the CPU, and the CPU sends a signal to the driving part, and the driving part controls the on and off of the thyristor.

[0069] When the automatic switch is turned on for forward rotation, the first winding M1 is the main winding and the second winding M2 is the auxiliary winding. A running capacitor CR is connected between the first winding M1 and the second winding M2. One end of the running capacitor CR is connected to the second terminal V1, and the other end is connected to the fourth terminal Z1. The fourth terminal Z1 is connected to a starting capacitor CS. The other end of the starting capacitor CS is connected to the third terminal V2. The other end of the third terminal V2 is connected to a thyristor. The other end of the thyristor is connected to the second terminal V1. The second terminal V1 is connected to the running capacitor CR, thus forming a set of interlocking switches.

[0070] When the automatic switch is turned on for reverse rotation, the second winding M2 is the main winding and the first winding M1 is the auxiliary winding. The second winding M2 is connected to the second terminal V1, and the first winding M1 is connected to the fourth terminal Z1. The fourth terminal Z1 is connected to the starting capacitor CS. The other end of the starting capacitor CS is connected to the third terminal V2. The other end of the third terminal V2 is connected to the thyristor. The other end of the thyristor is connected to the second terminal V1, thus forming another set of interlocking switches.

[0071] Working principle: After the power supply is connected, the sampling signal and the signal for triggering V2 are transmitted to the CPU, and the CPU emits a signal to the driving part to control the thyristor switch.

[0072] The shorting piece P1 shorts the fifth terminal U2 and the second terminal V1, and the shorting piece P2 shorts the sixth terminal U1 and the first terminal Z2. The shorting pieces N1 and N2 are not connected. The first winding M is the main winding and the second winding ST is the auxiliary winding. A running capacitor CR is connected between the first winding M and the second winding ST. One end of the running capacitor CR is connected to the second terminal V1, and the other end is connected to the fourth terminal Z1. The fourth terminal Z1 is connected to the starting capacitor CS. The other end of the starting capacitor CS is connected to the third terminal V2. The other end of the third terminal V2 is connected to the thyristor. The other end of the thyristor is connected to the second terminal V1. The second terminal V1 is connected to the running capacitor CR, thus starting the forward rotation of the motor.

[0073] The shorting piece N1 shorts the fifth terminal U2 and the first terminal Z2, and the shorting piece N2 shorts the sixth terminal U1 and the second terminal V1. The shorting pieces N1 and N2 are not connected. The first winding M is the main winding and the second winding ST is the auxiliary winding. A running capacitor CR is connected between the first winding M and the second winding ST. One end of the running capacitor CR is connected to the second terminal V1, and the other end is connected to the fourth terminal Z1. The fourth terminal Z1 is connected to the starting capacitor CS. The other end of the starting capacitor CS is connected to the third terminal V2. The other end of the third terminal V2 is connected to the thyristor. The other end of the thyristor is connected to the second terminal V1. The second terminal V1 is connected to the running capacitor CR, thus starting the reverse rotation of the motor.

[0074] Working principle: After the power supply is connected, the forward and reverse operations are controlled according to the different short-circuiting methods of the short-circuiting pieces P1, P2, N1, and N2. At the same time, the sampling signal and the signal triggering the third terminal V2 are transmitted to the CPU, and the CPU emits a signal to the driving part, and the driving part controls the on-off of the thyristor.

[0075] Electrical signal transmission and closing relationship: The second terminal V1 and the third terminal V2 have the function of detecting and collecting signals. The third terminal V2 detects the signal of the motor voltage, and the second terminal V1 detects the signal of the input power supply. After the signal sampling is completed, it will be automatically uploaded to the CPU, and the CPU controls the opening and closing of the switch according to the commonly used programming method in the prior art. This solution is designed for application in harsh industrial environments. The CPU has an additional function of rapid response compared with the previous electronic centrifugal switch, uses flexible instructions, and the functions achieved exceed those of the commonly used electronic centrifugal switch, effectively improving work efficiency and preventing short circuits.

[0076] In one embodiment, the step S2 of respectively preprocessing each of the first signal and the second signal to obtain a first target signal and a second target signal includes:

[0077] S201: Convert the first signal into a first target signal according to a preset first conversion method, and convert the second signal into a second target signal according to a preset second conversion method; wherein, the first target signal and the second target signal have the same dimension.

[0078] As described in the above step S201, wherein, the first conversion method is to convert the first signal into a corresponding numerical value or vector, which is a pre-set corresponding relationship table. Similarly, the second conversion method is to convert the second signal into a corresponding numerical value or vector, and specifically, the corresponding relationship table is pre-set. It should be noted that the dimensions of the first target signal and the second target signal are preferably kept consistent for subsequent calculations.

[0079] In one embodiment, after the step S4 of obtaining the real-time first signal and the real-time second signal through the detection unit, it further includes:

[0080] S501: Determine whether both the real-time first signal and the real-time second signal are within a preset range;

[0081] S502: If both are within the preset range, then execute the step of converting to the real-time first target signal and the real-time second target signal;

[0082] S503: If not within the preset range, then control the motor switch to close.

[0083] As described in the above steps S501 - S503, in the actual process, the motor may be damaged. Therefore, the real - time first signal and the real - time second signal are not within the preset range. At this time, the circuit loop should be closed to avoid other accidents.

[0084] Referring to Figure 3 , the present invention also provides an AC motor starting control device, which is realized through a starting control circuit. The starting control circuit includes a power supply, a CPU, a motor switch, a motor, and a plurality of detection units. The motor switch is controlled by the CPU and connected. Each of the detection units is connected to the CPU. The power supply, the motor switch, and the motor form a loop. The AC motor starting control device includes:

[0085] An acquisition module 10, configured to acquire multiple groups of signal data and the starting instructions corresponding to each group of signal data; wherein, a group of signal data includes a first signal of the motor voltage and a second signal of the input power supply;

[0086] A pre - processing module 20, configured to pre - process each of the first signals and the second signals respectively to obtain a first target signal and a second target signal;

[0087] A first input module 30, configured to input each group of the first target signals and the starting instructions into a generation model in a GAN network model, and input the second target signals and the starting instructions into a discriminant model in the GAN network model for training to obtain a trained motor control model network model;

[0088] A conversion module 40, configured to acquire real - time first signals and real - time second signals through the detection unit and convert them into real - time first target signals and real - time second target signals;

[0089] A second input module 50, configured to input the real - time first target signals and the real - time second target signals into the motor control model network model to obtain real - time starting instructions;

[0090] A control module 60, configured to control the motor switch according to the real - time starting instructions.

[0091] Furthermore, the first input module 30 includes:

[0092] An input sub - module, configured to input the first target signal into the generation model to obtain an optimal prediction value, input the starting instruction into the generation model, and initially train the generation model through the formula and obtain a temporarily predicted value after training and a first intermediate model, and input the second target signal and and a start instruction are input into the discrimination model, and the discrimination model is initially trained through the formula to obtain a second intermediate model; where , represents the parameter set of the generation model, represents the parameter set of the discrimination model, is the best predicted value;

[0093] The training sub-module is used to perform secondary training on the first intermediate model and the second intermediate model according to the formula to obtain a motor control model network model after the training is completed; where means taking the minimum value of and the maximum value of on the premise of satisfying the above formula.

[0094] In one embodiment, the AC motor starting control circuit further includes: the motor switch is a thyristor of the motor switch, and the thyristor of the motor switch is connected to the first terminal Z2, the second terminal V1, the third terminal V2, and the fourth terminal Z1 of the motor, the winding, and the capacitor; the capacitor includes a running capacitor CR and a starting capacitor CS, the running capacitor CR is connected to the winding, and both ends of the starting capacitor CS are respectively connected to the third terminal V2 and the fourth terminal Z1; both ends of the thyristor are respectively connected to the second terminal V1 and the third terminal V2; the second terminal V1 is used to collect the signal of the input power supply and send the sampled signal to the CPU, the fourth terminal is used to collect the signal of the motor voltage and send the sampled signal to the CPU, and the CPU controls the opening and closing of the thyristor through a driving module.

[0095] In one embodiment, the preprocessing module 20 includes:

[0096] The conversion sub-module is used to convert the first target signal into a first target signal according to a preset first conversion method, and convert the second signal into a second target signal according to a preset second conversion method; where the dimensions of the first target signal and the second target signal are the same.

[0097] In one embodiment, the AC motor starting control device further includes:

[0098] The judgment module is used to judge whether both the real-time first signal and the real-time second signal are within a preset range;

[0099] The execution module is used to, if both are within the preset range, execute the step of converting into the real-time first target signal and the real-time second target signal;

[0100] A control module, configured to control the motor switch to turn off if it is not within a preset range.

[0101] Advantages of the present invention: By obtaining multiple groups of signal data and the corresponding start instructions for each group of signal data to train the GAN network, and using the trained motor control model network model to analyze and process the real-time signal data, the real-time start instruction can be obtained, and the motor switch is controlled according to the real-time start instruction, thereby realizing the automatic generation of the real-time start instruction, without manual operation, and the corresponding start instruction can be generated according to the detected data, improving the work efficiency and realizing intelligent control.

[0102] Referring to Figure 4 , in an embodiment of the present application, a computer device is further provided. The computer device may be a server, and its internal structure may be as Figure 4 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store various signal data, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it can implement the AC motor start control method described in any of the above embodiments.

[0103] Those skilled in the art can understand that Figure 4 the structure shown in

[0104] is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.

[0105] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in this application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, there are various forms of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0106] It should be noted that in this text, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that includes a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, apparatus, article, or method that includes the element.

[0107] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0108] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0109] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A method for starting and controlling an AC motor, characterized in that: The method is implemented by a startup control circuit, which includes a power supply, a CPU, a motor switch, a motor, and a plurality of detection units. The motor switch is controlled by the CPU, and each of the detection units is connected to the CPU. The power supply, the motor switch, and the motor form a loop. The AC motor startup control method includes: Acquire multiple groups of signal data and start instructions corresponding to each group of signal data; wherein one group of signal data includes a first signal of motor voltage and a second signal of input power; Preprocessing each of the first signal and the second signal respectively to obtain a first target signal and a second target signal; Inputting each group of the first target signal and the start instruction into a generation model in a GAN network model, and inputting the second target signal and the start instruction into a discrimination model in a GAN network model for training, to obtain a trained motor control model network model; Acquire a real-time first signal and a real-time second signal through a detection unit, and convert them into a real-time first target signal and a real-time second target signal; Inputting the real-time first target signal and the real-time second target signal into the motor control model network model to obtain a real-time start instruction; Controlling the motor switch according to the real-time start instruction; The step of inputting each group of the first target signal and the start instruction into the generation model in the GAN network model, and inputting the second target signal and the start instruction into the discrimination model in the GAN network model for training to obtain a trained motor control model network model includes: The first target signal Input into the generative model to obtain the best prediction value, and then Input into the generative model, through the formula Perform initial training on the generative model and obtain the temporary prediction value after training and the first intermediate model, and the second target signal And the startup command Input into the discriminant model, through the formula The discriminant model is initially trained to obtain a second intermediate model; wherein, , , represents the parameter set of the generative model, represents the parameter set of the discriminant model, is the best predicted value; According to the formula The first intermediate model and the second intermediate model are trained twice, and a motor control model network model is obtained after the training is completed; wherein It means that under the premise of satisfying the above formula, The minimum value of The maximum value of .

2. The AC motor starting control method according to claim 1, characterized in that: The AC motor starting control circuit also includes: the motor switch is the motor switch thyristor, the motor switch thyristor is connected to the first terminal Z2, the second terminal V1, the third terminal V2 and the fourth terminal Z1, the winding, and the capacitor of the motor; the capacitor includes an operating capacitor CR and a starting capacitor CS, the operating capacitor CR is connected to the winding, and the two ends of the starting capacitor CS are respectively connected to the third terminal V2 and the fourth terminal Z1; the two ends of the thyristor are respectively connected to the second terminal V1 and the third terminal V2; the second terminal V1 is used to collect the signal of the input power supply and send the signal of the input power supply to the CPU, the fourth terminal is used to collect the signal of the motor voltage and send the signal of the motor voltage to the CPU, and the CPU controls the opening and closing of the thyristor through a driving module.

3. The AC motor starting control method according to claim 1, characterized in that: The step of preprocessing each of the first signal and the second signal to obtain a first target signal and a second target signal comprises: The first target signal is converted into a first target signal according to a preset first conversion method, and the second signal is converted into a second target signal according to a preset second conversion method; wherein the dimensions of the first target signal and the second target signal are the same.

4. The AC motor starting control method according to claim 1, characterized in that: After the step of acquiring the real-time first signal and the real-time second signal by the detection unit, the method further includes: Determining whether the real-time first signal and the real-time second signal are both within a preset range; If both are within the preset range, the steps of converting into a real-time first target signal and a real-time second target signal are executed; If it is not within the preset range, the motor switch is controlled to be turned off.

5. An AC motor starting control device, characterized in that: It is realized by a startup control circuit, the startup control circuit includes a power supply, a CPU, a motor switch, a motor and a plurality of detection units, the motor switch is controlled by the CPU, each of the detection units is connected to the CPU, the power supply, the motor switch and the motor form a loop, and the AC motor startup control device includes: An acquisition module, used to acquire multiple groups of signal data and start instructions corresponding to each group of signal data; wherein a group of signal data includes a first signal of motor voltage and a second signal of input power; A preprocessing module, used for preprocessing each of the first signal and the second signal to obtain a first target signal and a second target signal; A first input module is used to input each group of the first target signal and the start instruction into a generation model in a GAN network model, and input the second target signal and the start instruction into a discrimination model in the GAN network model for training, so as to obtain a trained motor control model network model; A conversion module, used for acquiring a real-time first signal and a real-time second signal through a detection unit, and converting them into a real-time first target signal and a real-time second target signal; A second input module, used for inputting the real-time first target signal and the real-time second target signal into the motor control model network model to obtain a real-time start instruction; A control module, used for controlling the motor switch according to the real-time start instruction; The first input module comprises: An input submodule is used to convert the first target signal Input into the generative model to obtain the best prediction value, and then Input into the generative model, through the formula Perform initial training on the generative model and obtain the temporary prediction value after training and the first intermediate model, and the second target signal And the startup command Input into the discriminant model, through the formula The discriminant model is initially trained to obtain a second intermediate model; wherein, , , represents the parameter set of the generative model, represents the parameter set of the discriminant model, is the best predicted value; The training submodule is used to The first intermediate model and the second intermediate model are trained twice, and a motor control model network model is obtained after the training is completed; wherein It means that under the premise of satisfying the above formula, The minimum value of The maximum value of .

6. The AC motor starting control device according to claim 5, characterized in that: The AC motor starting control circuit also includes: the motor switch is the motor switch thyristor, the motor switch thyristor is connected to the first terminal Z2, the second terminal V1, the third terminal V2 and the fourth terminal Z1, the winding, and the capacitor of the motor; the capacitor includes an operating capacitor CR and a starting capacitor CS, the operating capacitor CR is connected to the winding, and the two ends of the starting capacitor CS are respectively connected to the third terminal V2 and the fourth terminal Z1; the two ends of the thyristor are respectively connected to the second terminal V1 and the third terminal V2; the second terminal V1 is used to collect the signal of the input power supply and send the signal of the input power supply to the CPU, the fourth terminal is used to collect the signal of the motor voltage and send the signal of the motor voltage to the CPU, and the CPU controls the opening and closing of the thyristor through a driving module.

7. The AC motor starting control device according to claim 5, characterized in that: The preprocessing module comprises: A conversion submodule is used to convert the first target signal into a first target signal according to a preset first conversion method, and to convert the second signal into a second target signal according to a preset second conversion method; wherein the first target signal and the second target signal have the same dimension.

8. The AC motor starting control device according to claim 5, characterized in that: The AC motor starting control device further includes: A judging module, used for judging whether the real-time first signal and the real-time second signal are both within a preset range; An execution module, used for executing the step of converting into a real-time first target signal and a real-time second target signal if both are within a preset range; The control module is used to control the motor switch to turn off if it is not within a preset range.

Images