Search

CN-121995127-A - Method, system, equipment and medium for rapidly detecting high-speed electromagnetic valve

CN121995127ACN 121995127 ACN121995127 ACN 121995127ACN-121995127-A

Abstract

The invention provides a rapid detection method of a high-speed electromagnetic valve, which comprises the steps of S1, setting detection input signals, directly loading the detection input signals on a single electromagnetic valve part to obtain electromagnetic valve current signals in different quality states, S2, building a neural network model, inputting the electromagnetic valve current signals into the neural network model for training to obtain a quality inspection model, S3, deploying the quality inspection model into inspection equipment, analyzing the electromagnetic valve current signals acquired in real time, and outputting an electromagnetic valve quality report. The invention utilizes the neural network model, and realizes the quick judgment of the quality state of the electromagnetic valve by analyzing the electromagnetic valve current under the specific pulse voltage, thereby solving the problems of low inspection precision and long inspection time of the high-speed electromagnetic valve. The electromagnetic valve part detection device directly detects electromagnetic valve parts, does not need clamping, does not need to consider the gap between the electromagnetic valve and the armature, and has the characteristics of simplicity in operation and high recognition precision.

Inventors

  • XU HUI
  • Huang du
  • GU ZIMING
  • LI DONG
  • CHEN KANG
  • GUO YUAN

Assignees

  • 重庆红江机械有限责任公司

Dates

Publication Date
20260508
Application Date
20241106

Claims (7)

  1. 1. The rapid detection method of the high-speed electromagnetic valve is characterized by comprising the following steps of: s1, setting a detection input signal, and directly loading the detection input signal onto a single electromagnetic valve part to obtain electromagnetic valve current signals in different quality states; s2, building a neural network model, inputting electromagnetic valve current signals into the neural network model for training, and obtaining a quality inspection model; And S3, deploying the quality inspection model into inspection equipment, analyzing electromagnetic valve current signals acquired in real time, and outputting an electromagnetic valve quality report.
  2. 2. The rapid detection method of high-speed solenoid valve according to claim 1, wherein the setting of the detection input signal, directly loading the detection input signal on an unassembled single solenoid valve part, obtaining solenoid valve current signals in different quality states, comprises: s101, determining voltage amplitude and voltage frequency when a single solenoid valve is detected according to actual control voltage and voltage frequency given by a solenoid valve controller to be detected; S102, setting detection input signals consistent with the voltage assignment and the voltage frequency; s103, loading the detection input signal to a detected electromagnetic valve terminal to obtain a current signal of the electromagnetic valve; S104, repeating the step S103 until electromagnetic valve current signals in different quality states are collected, and classifying and storing.
  3. 3. The method for rapidly detecting the high-speed electromagnetic valve according to claim 2, wherein the building of the neural network model, inputting the electromagnetic valve current signal into the neural network model for training, and obtaining the quality inspection model, comprises the following steps: s201, marking quality state labels on the electromagnetic valve current signals, and classifying the electromagnetic valve current signals into a training data set and a checking data set; S202, preprocessing a training data set by adopting a VMD algorithm to obtain a solenoid valve current modal characteristic component; S203, setting parameters, building a neural network model, inputting the electromagnetic valve current modal characteristic components into the neural network model for training, and outputting a quality inspection model.
  4. 4. The rapid detection method of high-speed electromagnetic valve according to claim 3, wherein the building of the neural network model, inputting electromagnetic valve current signals into the neural network model for training, obtaining a quality inspection model, further comprises: S204, inputting the inspection data set into the quality verification model for verification, and optimizing parameters of the neural network model according to a verification result until the verification result of the neural network model meets verification accuracy.
  5. 5. A rapid detection system for a high-speed solenoid valve, comprising: The signal sampling module is used for setting a detection input signal, directly loading the detection input signal onto a single electromagnetic valve part, and obtaining electromagnetic valve current signals in different quality states; The model training module is used for building a neural network model, inputting electromagnetic valve current signals into the neural network model for training, and obtaining a quality inspection model; the detection module is used for deploying the quality inspection model into inspection equipment, analyzing electromagnetic valve current signals acquired in real time and outputting electromagnetic valve quality reports.
  6. 6. An electronic device comprising a processor, a storage medium and a computer program stored in the storage medium, characterized in that the computer program, when executed by the processor, implements the high-speed solenoid valve rapid detection method according to any one of claims 1 to 4.
  7. 7. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, implements the high-speed solenoid valve rapid detection method of any one of claims 1 to 4.

Description

Method, system, equipment and medium for rapidly detecting high-speed electromagnetic valve Technical Field The invention belongs to the technical field of high-speed electromagnetic valves, and particularly relates to a method, a system, equipment and a medium for rapidly detecting a high-speed electromagnetic valve. Background The quality state of the high-speed electromagnetic valve is one of the most important parts of an electric control system, directly influences whether the quality of a product meets the requirement, and the quality of the electromagnetic valve is detected at present mainly by detecting electromagnetic force. Because the minimum distance between the armature and the electromagnetic valve is less than 0.1 millimeter, the requirement on the positioning precision of the inspection equipment is extremely high, manual repeated adjustment is needed, but the measurement result is often inaccurate due to the errors of manual clamping and equipment errors, and the test cost and the after-sale cost are increased. Disclosure of Invention Aiming at the problems in the prior art, the invention provides a rapid detection method of a high-speed electromagnetic valve, which aims to solve the technical problems that the measurement result is often inaccurate due to the errors of manual clamping and equipment errors in the prior art, and the test cost and the after-sale cost are increased. The invention provides a rapid detection method of a high-speed electromagnetic valve, which comprises the following steps: s1, setting a detection input signal, and directly loading the detection input signal onto a single electromagnetic valve part to obtain electromagnetic valve current signals in different quality states; s2, building a neural network model, inputting electromagnetic valve current signals into the neural network model for training, and obtaining a quality inspection model; And S3, deploying the quality inspection model into inspection equipment, analyzing electromagnetic valve current signals acquired in real time, and outputting an electromagnetic valve quality report. Optionally, the setting the detection input signal, directly loading the detection input signal on an unassembled single electromagnetic valve part, and obtaining electromagnetic valve current signals in different quality states, including: s101, determining voltage amplitude and voltage frequency when a single solenoid valve is detected according to actual control voltage and voltage frequency given by a solenoid valve controller to be detected; S102, setting detection input signals consistent with the voltage assignment and the voltage frequency; s103, loading the detection input signal to a detected electromagnetic valve terminal to obtain a current signal of the electromagnetic valve; S104, repeating the step S103 until electromagnetic valve current signals in different quality states are collected, and classifying and storing. Optionally, the building a neural network model, inputting the electromagnetic valve current signal into the neural network model for training, to obtain a quality inspection model, includes: s201, marking quality state labels on the electromagnetic valve current signals, and classifying the electromagnetic valve current signals into a training data set and a checking data set; S202, preprocessing a training data set by adopting a VMD algorithm to obtain a solenoid valve current modal characteristic component; S203, setting parameters, building a neural network model, inputting the electromagnetic valve current modal characteristic components into the neural network model for training, and outputting a quality inspection model. Optionally, the building a neural network model, inputting the electromagnetic valve current signal into the neural network model for training to obtain a quality inspection model, and further includes: S204, inputting the inspection data set into the quality verification model for verification, and optimizing parameters of the neural network model according to a verification result until the verification result of the neural network model meets verification accuracy. The invention also provides a rapid detection system of the high-speed electromagnetic valve, which comprises the following steps: The signal sampling module is used for setting a detection input signal, directly loading the detection input signal onto a single electromagnetic valve part, and obtaining electromagnetic valve current signals in different quality states; The model training module is used for building a neural network model, inputting electromagnetic valve current signals into the neural network model for training, and obtaining a quality inspection model; the detection module is used for deploying the quality inspection model into inspection equipment, analyzing electromagnetic valve current signals acquired in real time and outputting electromagnetic valve quality reports. The invention also provide