Air conditioning system safety valve based on vision assistance

Abstract

The invention discloses an air-conditioning system safety valve based on visual assistance, belongs to the technical field of visual assistance, and solves the problems that the problems have certain concealment, the dynamic pressure fluctuation condition is difficult to judge through a static image for the visual identification technology, and whether the rigidity of a spring in the safety valve is appropriate or not. Comprising a safety valve body, a three-axis vibration sensor arranged on a valve body of the safety valve body and used for collecting and outputting vibration signals, and a broadband pressure sensor arranged in an inlet of the safety valve body and used for collecting dynamic pressure changes in the safety valve body. The vibration and pressure conditions of the safety valve are detected through the three-axis vibration sensor and the broadband pressure sensor, and primary detection is completed; two-stage detection is carried out in cooperation with photoelectric pulse statistics and visual identification, final judgment is output in combination with two-stage detection results, it is ensured that frequency hopping or flutter of the safety valve is accurately identified, and the situation that the accuracy is affected by a single visual identification technology is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of vision assistance, and particularly to a safety valve for an air conditioning system based on vision assistance. Background Art

[0002] The safety valve of an air conditioning system is an important component to ensure the safe operation of air conditioning equipment. It is installed on the refrigeration system of the air conditioner or the exhaust pipe of the air conditioner compressor. Its main function is to limit the pressure in the system and prevent damage to the system caused by excessive or too low pressure. The safety valve consists of components such as a valve body, a valve core, a spring, and an adjusting nut. It is normally in a closed state during normal operation. When the system pressure exceeds the set safety value, the safety valve will automatically open to release the excess pressure and restore the system pressure to normal, thereby protecting key components such as compressors and condensers from damage. At the same time, it can also prevent safety hazards caused by refrigerant leakage. In some air conditioning systems, the safety valve is also equipped with a pressure gauge to facilitate technicians to monitor the system pressure in real time. Its structural design is usually spring type or lever type, and the opening pressure is set by adjusting the elastic force of the spring or the weight of the lever. The performance of the safety valve of the air conditioning system directly affects the safety and reliability of the air conditioning system. Regular inspection and calibration of the safety valve are important links in air conditioning maintenance to ensure that it can work properly at critical moments and guarantee the stable operation of the air conditioning system and the safety of users.

[0003] During the daily operation of the air conditioning system, the phenomenon of frequent jumping or fluttering of the safety valve often occurs. The reasons are as follows. On the one hand, it may be that the spring stiffness is too large or the position of the adjusting ring is improper. When the spring stiffness is too large, after the valve disc opens, under the action of the large elastic force of the spring, the valve disc quickly returns to its seat. However, during the return process, due to the collision between the valve disc and the valve seat and the impact of the fluid, the valve disc will open again, and so on, resulting in frequent jumping or fluttering. Improper position of the adjusting ring will change the return pressure and opening and closing characteristics of the safety valve, making the valve disc unable to return to its seat stably after opening, thereby causing fluttering. On the other hand, excessive resistance in the discharge pipeline leading to back pressure fluctuations is also one of the common reasons. When the back pressure fluctuates, the force on the valve disc also changes accordingly. Once this change is frequent and large in amplitude, it will cause the valve disc to jump or flutter frequently.

[0004] However, these problems are somewhat concealed. For vision recognition technology, it is very difficult to judge the dynamic pressure fluctuation situation through static images, and whether the stiffness of the spring inside the safety valve is appropriate. At the same time, in the actual operation scenario, the complex pipeline layout and obstacles will further increase the difficulty of vision recognition, making these problems difficult to be recognized and judged in a timely and accurate manner.

[0005] Therefore, a safety valve for an air conditioning system based on vision assistance is proposed to solve or alleviate the above problems. Summary of the Invention

[0006] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a safety valve for an air-conditioning system based on visual assistance.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: A visually assisted safety valve for an air conditioning system includes a safety valve body, a three-axis vibration sensor disposed on the valve body of the safety valve body and collecting and outputting vibration signals, a broadband pressure sensor disposed within the inlet of the safety valve body and collecting dynamic pressure changes within the safety valve body, an image acquisition unit disposed on one side of the safety valve body and covering the actuator in the safety valve body, and a photoelectric encoder drivingly connected to the actuator in the safety valve body. It also includes a signal preprocessing module, a vibration spectrum separation module, a phase coherence detection module, a dynamic fault classification module, a visual motion verification module, and a communication and display module; The input end of the signal preprocessing module is connected to the output end of the broadband pressure sensor, and the signal preprocessing module separates the dynamic pressure change into low-frequency, medium-frequency, and high-frequency channel signals and transmits them to the dynamic fault classification module and the phase coherence detection module; The input end of the vibration spectrum separation module is connected to the output end of the triaxial vibration sensor, and the triaxial vibration sensor extracts the frequency band energy characteristics of the vibration signal to the dynamic fault classification module; The output end of the phase coherent detection module is connected to the input end of the dynamic fault classification module, and the phase coherent detection module receives the intermediate frequency channel signal and the frequency band energy characteristics to calculate the phase difference between the pressure fluctuation and the vibration and sends it to the dynamic fault classification module; The output end of the dynamic fault classification module is connected to the input end of the communication and display module, and the dynamic fault classification module outputs a fault code through logical judgment; The input end of the visual motion verification module is connected to the output end of the photoelectric encoder and the picture acquisition unit respectively, and the output end of the visual motion verification module is also connected to the input end of the communication and display module. The visual motion verification module verifies the valve action frequency through visual data; The communication and display module is used to receive fault codes and verification results and output graded alarms.

[0008] Preferably, the signal preprocessing module separates the dynamic pressure change into low-frequency, medium-frequency, and high-frequency channel signals and transmits them to the dynamic fault classification module and the phase coherence detection module, specifically comprising the following steps: Separate the pressure signal of dynamic pressure changes through a third-order Sallen-Key filter; The low-frequency channel signal adopts a first-order low-pass filter with a frequency range of 0.1 to 2 Hz and a time constant set to 0.8 seconds to detect slow changes in pipeline resistance; The intermediate frequency channel signal uses a second-order band-pass filter with a frequency range of 5 to 20 Hz, a center frequency of 10 Hz, and a quality factor of 0.707, which is used to extract the periodic fluctuations of the regulating ring; The high-frequency channel signal uses a second-order high-pass filter with a frequency range of 50 to 200 Hz, a center frequency of 50 Hz, and a quality factor of 0.5, which is used to capture the transient impact of the spring stiffness.

[0009] Preferably, the triaxial vibration sensor extracts the band energy characteristics of the vibration signal, which specifically includes the following steps: Separate the vibration signal through a programmable filter to obtain the low-frequency band energy characteristics and the high-frequency band energy characteristics. The frequency range of the low-frequency band energy characteristics is 5 to 50 Hz, which corresponds to flutter detection, and the frequency range of the high-frequency band energy characteristics is 50 to 200 Hz, which corresponds to frequency jump detection.

[0010] Preferably, the dynamic fault classification module outputs a fault code through logical judgment, which specifically includes the following steps: Based on the baseline tracking circuit in the dynamic fault classification module, calculate the pressure baseline in real time and generate a dynamic threshold; In the dynamic fault classification module, extract the pressure channel energy, vibration band energy, and phase difference characteristics, and perform weighted fusion; Through the fuzzy decision-making circuit in the dynamic fault classification module, combine the threshold condition and the membership function to determine the fault type.

[0011] Preferably, based on the baseline tracking circuit in the dynamic fault classification module, calculate the pressure baseline in real time and generate a dynamic threshold, which specifically includes the following steps: The baseline tracking circuit in the dynamic fault classification module uses first-order inertial filtering. The current baseline voltage value is 95% of the previous baseline voltage value plus 5% of the current input voltage value; The adaptive threshold circuit in the dynamic fault classification module is implemented by a comparator. The dynamic threshold is the sum of the baseline voltage value and three times the static noise standard deviation, where the static noise standard deviation is determined through static calibration; The parameters of the dynamic threshold are dynamically adjusted through the serial clock pin and data input pin of the digital potentiometer in the dynamic fault classification module.

[0012] Preferably, in the dynamic fault classification module, extract the pressure channel energy, vibration band energy, and phase difference characteristics, and perform weighted fusion, which specifically includes the following steps: Normalize the input low-frequency channel signal, intermediate frequency channel signal, high-frequency channel signal, low-frequency band energy characteristics, and high-frequency band energy characteristics; The signals after normalization are respectively multiplied by preset weight coefficients and then added together to obtain a comprehensive fault score, where the weight of the low-frequency channel signal is 0.3, the weight of the medium-frequency channel signal is 0.25, the weight of the high-frequency channel signal is 0.25, the weight of the low-frequency band energy feature is 0.1, and the weight of the high-frequency band energy feature is 0.1.

[0013] Preferably, the fuzzy decision-making circuit in the dynamic fault classification module is used to determine the fault type by combining the threshold condition and the membership function, which specifically includes the following steps: The determination condition for excessive spring stiffness is that the comprehensive fault score exceeds 1.5, at the same time, the high-frequency channel signal exceeds three times its static standard deviation, and the phase difference between pressure and vibration is greater than 60 degrees; The determination condition for improper position of the adjusting ring is that the medium-frequency channel signal exceeds twice its static standard deviation, and the ratio of the peak-to-peak value of pressure fluctuation to the mean value is greater than 0.4; The determination condition for excessive pipeline resistance is that the low-frequency channel signal exceeds 2.5 times its static standard deviation, and the baseline voltage change rate exceeds 0.05 volts per second.

[0014] Preferably, the visual action verification module verifies the valve action frequency through visual data, which specifically includes the following steps: The optoelectronic encoder captures transient action anomalies by collecting the rising edge of optoelectronic pulses, and the valve action frequency is the number of rising edges of optoelectronic pulses; The camera captures images, calculates the displacement trend through the frame difference method, and the displacement change amount is the mean value of the pixel gray value differences between two adjacent frames of images. The threshold is set to 20 gray levels per frame. If the displacement trend exceeds 20 gray levels per frame, it is determined as an effective action; Calculate the action frequency according to the number of effective actions / total number of frames * time interval between two adjacent frames. If the valve action frequency - action frequency < 0.2 * valve action frequency, the output result is that the verification passes.

[0015] Preferably, the communication and display module is used to receive the fault code and verification result and output a hierarchical alarm, which specifically includes the following steps: Receive the fault type output by the dynamic fault classification module and receive the output result of the visual action verification module as verification passed, then transmit information externally and alarm.

[0016] The present invention has the following beneficial effects: The present invention detects the vibration and pressure conditions of the safety valve body through a three-axis vibration sensor and a broadband pressure sensor, and then completes the primary detection of frequency jumping or fluttering of the safety valve body. In addition, it cooperates with photoelectric pulse statistics of frequency jumping or fluttering conditions and visual recognition for secondary detection, and combines the results of the primary detection and the secondary detection to output the final result, ensuring accurate identification when the safety valve body has frequency jumping or fluttering conditions, and avoiding the influence of the single use of visual recognition technology on the accuracy of the final problem identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic structural diagram of the present invention.

[0019] In the figure: 1, safety valve body; 2, broadband pressure sensor; 3, three-axis vibration sensor; 4, signal preprocessing module; 5, vibration spectrum separation module; 6, phase coherence detection module; 7, dynamic fault classification module; 8, visual action verification module; 9, communication and display module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and illustrated in the drawings here can be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the present invention claimed, but merely represents the selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0022] It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0023] In the description of the present invention, it should be understood that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, or are the orientation or position relationship in which the product of the invention is usually placed when in use, or are the orientation or position relationship commonly understood by those skilled in the art. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0024] Furthermore, the terms “first,” “second,” “third,” etc., are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0025] In the description of the present invention, it should also be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0026] A visually assisted air conditioning system safety valve, such as Figure 1 As shown, it includes a safety valve body 1, a three-axis vibration sensor 3 provided on the valve body of the safety valve body 1 and collecting and outputting vibration signals, a broadband pressure sensor 2 provided in the inlet of the safety valve body 1 and collecting dynamic pressure changes in the safety valve body 1, an image acquisition unit provided on one side of the safety valve body 1 and having a field of view covering the actuator in the safety valve body 1, and a photoelectric encoder drivingly connected to the actuator in the safety valve body 1. The image acquisition unit is a camera. It also includes a signal preprocessing module 4, a vibration spectrum separation module 5, a phase coherence detection module 6, a dynamic fault classification module 7, a visual motion verification module 8, and a communication and display module 9.

[0027] The input end of the signal preprocessing module 4 is connected to the output end of the broadband pressure sensor 2, the input end of the vibration spectrum separation module 5 is connected to the output end of the three-axis vibration sensor 3, the output end of the phase coherence detection module 6 is connected to the input end of the dynamic fault classification module 7, the output end of the dynamic fault classification module 7 is connected to the input end of the communication and display module 9, the input end of the visual motion verification module 8 is respectively connected to the output ends of the photoelectric encoder and the picture acquisition unit, and the output end of the visual motion verification module 8 is also connected to the input end of the communication and display module 9.

[0028] The signal preprocessing module 4 includes a DAC121S101 digital-to-analog converter, an INA333 instrumentation amplifier, a first resistor, an LTC1562 anti-aliasing filter, an OP07 operational amplifier, an LT1016 comparator, an LT1568 band-pass filter, a first AD633 multiplier, an AD827 differential amplifier, and an AD734 multiplier; The broadband pressure sensor 2 is of the model MS5803-14BA. The serial clock pin and the serial data pin of the broadband pressure sensor 2 are respectively connected to the serial clock input terminal and the serial data input terminal of the DAC121S101 digital-to-analog converter. The analog output pin of the DAC121S101 digital-to-analog converter is connected to the non-inverting input terminal of the INA333 instrumentation amplifier. The inverting input terminal of the INA333 instrumentation amplifier is grounded. The first resistor is connected in series between the two gain setting pins of the INA333 instrumentation amplifier. The output terminal of the INA333 instrumentation amplifier is connected to the input terminal of the LTC1562 anti-aliasing filter. The output terminal of the LTC1562 anti-aliasing filter is divided into three paths: Low-frequency channel: It is input through the OP07 operational amplifier. The output terminal of the OP07 operational amplifier is connected to the non-inverting input terminal of the LT1016 comparator; Intermediate-frequency channel: It is input through the positive input terminal of the LT1568 band-pass filter. The output terminal of the LT1568 band-pass filter is connected to the X input terminal of the first AD633 multiplier; High-frequency channel: It is input through the non-inverting input terminal of the AD827 differential amplifier. The output terminal of the AD827 differential amplifier is connected to the X input terminal of the AD734 multiplier.

[0029] The triaxial vibration sensor 3 is of the model ADXL345. The vibration spectrum separation module 5 includes an OPA2277 charge amplifier, an LTC1068 programmable filter, an AD736 RMS converter, a second resistor, a third resistor, a fourth resistor, a fifth resistor, a sixth resistor, and a seventh resistor; The X-axis output terminal of the triaxial vibration sensor 3 is connected to the non-inverting input terminal of the OPA2277 charge amplifier. The output terminal of the OPA2277 charge amplifier is connected to the input terminal of the LTC1068 programmable filter. The six-channel output terminals of the LTC1068 programmable filter are respectively connected to the six input terminals of the AD736 RMS converter. The six output terminals of the AD736 RMS converter are respectively connected to the input terminal of the dynamic fault classification module 7 after being connected in series with the second resistor, the third resistor, the fourth resistor, the fifth resistor, the sixth resistor, and the seventh resistor.

[0030] The phase coherence detection module 6 includes a CD4046 phase-locked loop, a second AD633 multiplier, and an OPA2188 integrator; The input end of the CD4046 phase-locked loop is connected to the output end of the intermediate-frequency channel of the signal preprocessing module 4, the output end of the CD4046 phase-locked loop is connected to the Y input end of the second AD633 multiplier, the X input end of the second AD633 multiplier is connected to the output end of the third channel of the vibration spectrum separation module 5, the Z input end of the second AD633 multiplier is connected to the input end of the OPA2188 integrator, and the output end of the OPA2188 integrator outputs the phase difference voltage to the input end of the dynamic fault classification module 7.

[0031] The dynamic fault classification module 7 includes an AD734 eight-channel analog multiplier, a DS1804 digital potentiometer, an OPA211 limiting amplifier, and a three-channel LM311 comparator array; The X input ends of the AD734 eight-channel analog multiplier are respectively connected to the output ends of the low-frequency channel, the intermediate-frequency channel, the high-frequency channel, and the six output ends of the AD736 effective value converter. The Y input end of the AD734 eight-channel analog multiplier sets weights through the serial clock end and data input end of the DS1804 digital potentiometer. The output end of the AD734 eight-channel analog multiplier is connected to the non-inverting input end of the OPA211 limiting amplifier. The output end of the OPA211 limiting amplifier is connected to the inverting input end of the three-channel LM311 comparator array. The non-inverting input ends of the three-channel LM311 comparator array are connected to the power supply after passing through the eighth resistor. The output ends of the three-channel LM311 comparator array are connected to the fault coding end of the communication and display module 9.

[0032] The visual action verification module 8 includes an STM32F407 microcontroller and a TXB0108 level conversion chip; The STM32F407 microcontroller is respectively connected to the photoelectric encoder and the camera. The clock pin and data output pin of the STM32F407 microcontroller are connected to the clock pin and data input pin of the communication and display module 9 after passing through the TXB0108 level conversion chip.

[0033] The communication and display module 9 includes a 74HC148 priority encoder and an RS485 driver chip. The enable end of the 74HC148 priority encoder is connected to the output end of the LM311 comparator in the dynamic fault classification module 7. The output end of the 74HC148 priority encoder is connected to the data input end of the RS485 driver chip. The differential output end of the RS485 driver chip is connected to the external RS485 bus to transmit information externally.

[0034] Preferably, the signal preprocessing module 4 separates the dynamic pressure change into low-frequency, intermediate-frequency, and high-frequency channel signals and transmits them to the dynamic fault classification module 7 and the phase coherence detection module 6, specifically including the following steps: Separate the pressure signal of the dynamic pressure change through a third-order Sallen-Key filter; The low-frequency channel signal uses a first-order low-pass filter with a frequency range of 0.1 to 2 Hz and a time constant set to 0.8 s to detect slow changes in pipeline resistance; The intermediate-frequency channel signal uses a second-order band-pass filter with a frequency range of 5 to 20 Hz, a center frequency of 10 Hz, and a quality factor of 0.707 to extract the periodic fluctuations of the regulating ring; The high-frequency channel signal uses a second-order high-pass filter with a frequency range of 50 to 200 Hz, a center frequency of 50 Hz, and a quality factor of 0.5 to capture the transient impact of spring stiffness.

[0035] Preferably, the triaxial vibration sensor 3 extracts the frequency band energy characteristics of the vibration signal, which specifically includes the following steps: Separate the vibration signal through a programmable filter to obtain the low-frequency band energy characteristics and the high-frequency band energy characteristics. The frequency range of the low-frequency band energy characteristics is 5 to 50 Hz, which corresponds to flutter detection, and the frequency range of the high-frequency band energy characteristics is 50 to 200 Hz, which corresponds to frequency jump detection.

[0036] Preferably, the dynamic fault classification module 7 outputs a fault code through logical judgment, which specifically includes the following steps: Based on the baseline tracking circuit in the dynamic fault classification module 7, calculate the pressure baseline in real time and generate a dynamic threshold; In the dynamic fault classification module 7, extract the energy of the pressure channel, the energy of the vibration frequency band, and the phase difference characteristics, and perform weighted fusion; Through the fuzzy judgment circuit in the dynamic fault classification module 7, combine the threshold conditions and the membership function to determine the fault type.

[0037] Preferably, based on the baseline tracking circuit in the dynamic fault classification module 7, calculate the pressure baseline in real time and generate a dynamic threshold, which specifically includes the following steps: The baseline tracking circuit in the dynamic fault classification module 7 uses first-order inertial filtering. The current baseline voltage value is 95% of the previous baseline voltage value plus 5% of the current input voltage value; The adaptive threshold circuit in the dynamic fault classification module 7 is implemented by a comparator. The dynamic threshold is the sum of the baseline voltage value and three times the static noise standard deviation, where the static noise standard deviation is determined through static calibration; The parameters of the dynamic threshold are dynamically adjusted through the serial clock pin and the data input pin of the digital potentiometer in the dynamic fault classification module 7.

[0038] Preferably, in the dynamic fault classification module 7, extract the energy of the pressure channel, the energy of the vibration frequency band, and the phase difference characteristics, and perform weighted fusion, which specifically includes the following steps: Normalize the input low-frequency channel signal, intermediate-frequency channel signal, high-frequency channel signal, low-frequency band energy feature, and high-frequency band energy feature; After normalization, each signal is multiplied by a preset weight coefficient and then added together to obtain a comprehensive fault score. Among them, the weight of the low-frequency channel signal is 0.3, the weight of the intermediate-frequency channel signal is 0.25, the weight of the high-frequency channel signal is 0.25, the weight of the low-frequency band energy feature is 0.1, and the weight of the high-frequency band energy feature is 0.1.

[0039] Preferably, through the fuzzy decision-making circuit in the dynamic fault classification module 7, combine the threshold condition and the membership function to determine the fault type. The specific steps are as follows: The determination condition for excessive spring stiffness is that the comprehensive fault score exceeds 1.5, at the same time, the high-frequency channel signal exceeds three times its static standard deviation, and the phase difference between pressure and vibration is greater than 60 degrees; The determination condition for improper adjustment ring position is that the comprehensive fault score exceeds 1.8, the intermediate-frequency channel signal exceeds twice its static standard deviation, and the ratio of the peak-to-peak value of pressure fluctuation to the mean value is greater than 0.4; The determination condition for excessive pipeline resistance is that the comprehensive fault score exceeds 2.2, the low-frequency channel signal exceeds 2.5 times its static standard deviation, and the baseline voltage change rate exceeds 0.05 volts per second.

[0040] Preferably, the visual action verification module 8 verifies the valve action frequency through visual data. The specific steps are as follows: The optoelectronic encoder captures the transient action anomaly by collecting the rising edge of the optoelectronic pulse, and the valve action frequency is the number of rising edges of the optoelectronic pulse; The camera captures images, calculates the displacement trend through the frame difference method. The displacement change amount is the mean value of the pixel gray value differences between two adjacent frames of images. The threshold is set to 20 gray levels per frame. If the displacement trend exceeds 20 gray levels per frame, it is determined as an effective action; Calculate the action frequency according to the number of effective actions / total number of frames * time interval between two adjacent frames. If the valve action frequency - action frequency < 0.2 * valve action frequency, the output result is that the verification passes.

[0041] Preferably, the communication and display module 9 is used to receive the fault code and verification result and output a hierarchical alarm. The specific steps are as follows: Receive the fault type output by the dynamic fault classification module 7 and receive that the output result of the visual action verification module 8 is that the verification passes, then transmit information externally and alarm.

[0042] After the air conditioning system is started, the broadband pressure sensor 2 collects the pressure data on the inlet side of the safety valve in real time, and transmits the digital signal to the DAC121S101 digital-to-analog converter to be converted into a 0-5V analog signal and then output to the INA333 instrumentation amplifier. After being amplified by the gain, the signal is output to the LTC1562 anti-aliasing filter. This filter decomposes the pressure signal into three frequency bands through a third-order Sallen-Key structure: the low-frequency channel signal passes through the input and output of the OP07 operational amplifier, and the pressure slow change caused by the resistance on the inlet side of the safety valve is detected through integral processing. Its output is connected to the LT1016 comparator and compared with the dynamic threshold; The intermediate-frequency channel signal passes through the input and output of the LT1568 band-pass filter, extracts the periodic fluctuation characteristics of the regulating ring and then inputs it to the X input terminal of the first AD633 multiplier; The high-frequency channel signal passes through the input and output of the AD827 differential amplifier, captures the high-frequency impact signal with excessive spring stiffness and inputs it to the X input terminal of the AD734 multiplier.

[0043] At the same time, the X-axis output terminal of the three-axis vibration sensor 3 is connected to the OPA2277 charge amplifier. The vibration signal is amplified and then output to the LTC1068 programmable filter. This filter separates the vibration signal into a low-frequency band and a high-frequency band. The low-frequency band is output to the AD736 RMS converter to detect the flutter energy, and the high-frequency band is output to the AD736 RMS converter to detect the frequency jump energy. The six RMS signals are respectively input to the dynamic fault classification module 7 through the resistor network.

[0044] In the dynamic threshold generation stage, the dynamic fault classification module 7 calculates the pressure baseline voltage in real time through the first-order inertial filtering algorithm. The baseline value is the sum of 95% of the previous moment's baseline voltage input by the OPA2188 integrator and 5% of the current input voltage, and is output to the LM311 comparator. The generated dynamic threshold is the baseline value plus three times the static noise standard deviation. The threshold signal is input to the three-way LM311 comparator array.

[0045] In the fault feature extraction and fusion stage, the AD734 analog multiplier receives the pressure low-frequency, intermediate-frequency, high-frequency, vibration low-frequency, and vibration high-frequency signals respectively. The weights of each channel are set through the DS1804 digital potentiometer, and the weights are 0.3, 0.25, 0.25, 0.1, and 0.1 respectively. The multiplication result is output to the OPA211 limiting amplifier, and after being amplified, the comprehensive fault score is output to the three-way LM311 comparator array and compared with the preset threshold to generate a 3-bit fault code.

[0046] In the phase coherence detection module 6, the CD4046 phase-locked loop receives the pressure intermediate frequency signal. The output VCO signal is input to the Y input terminal of the second AD633 multiplier. After multiplying with the vibration third-channel signal, the OPA2188 integrator receives the product signal and outputs the phase difference voltage to the dynamic fault classification module 7 for judging the pressure-vibration coherence.

[0047] In the visual action verification module 8, the output of the optical encoder is connected to the STM32F407 microcontroller. The valve action frequency is calculated by rising edge counting. At the same time, the camera captures the valve stem image at a rate of 10 frames per second, and calculates the average gray level difference of adjacent frame pixels by the frame difference method. If it exceeds 20 gray levels, it is determined as an effective action. The verification result is transmitted to the communication and display module 9 through the SPI interface via the TXB0108 level conversion chip.

[0048] In the communication and display module 9, the 74HC148 priority encoder enables to receive the fault code, and outputs the encoded signal to the RS485 driver chip to drive the RS485 bus to send differential signals.

[0049] Throughout the process, the multi-sensor data is strictly synchronized by timestamps. The frequency band separation of the pressure signal, the spectral analysis of the vibration energy, the coherence calculation of the phase difference, and the visual action verification form quadruple redundancy. The dynamic threshold avoids environmental interference, and the fuzzy decision logic ensures a low false alarm rate. From the capture of pressure shocks, the analysis of mechanical vibrations to the verification of action trajectories, it fully covers the detection requirements of three core faults: abnormal spring stiffness, regulator ring offset, and excessive pipeline resistance, avoiding the situation where problems cannot be accurately judged solely by visual recognition technology.

[0050] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An air conditioner system safety valve based on visual assistance, characterized in that, The invention comprises a safety valve body (1), a three-axis vibration sensor (3) arranged on the valve body in the safety valve body (1) and collecting and outputting a vibration signal, a broadband pressure sensor (2) arranged in the inlet of the safety valve body (1) and collecting dynamic pressure changes in the safety valve body (1), an image acquisition unit arranged on one side of the safety valve body (1) and having a field of view covering the actuator in the safety valve body (1), and a photoelectric encoder connected to the actuator in the safety valve body (1); It also includes a signal preprocessing module (4), a vibration spectrum separation module (5), a phase coherence detection module (6), a dynamic fault classification module (7), a visual motion verification module (8), and a communication and display module (9); The input end of the signal preprocessing module (4) is connected to the output end of the broadband pressure sensor (2), and the signal preprocessing module (4) separates the dynamic pressure change into low-frequency, medium-frequency, and high-frequency channel signals and transmits them to the dynamic fault classification module (7) and the phase coherence detection module (6); The input end of the vibration spectrum separation module (5) is connected to the output end of the three-axis vibration sensor (3), and the three-axis vibration sensor (3) extracts the frequency band energy characteristics of the vibration signal to the dynamic fault classification module (7); The output end of the phase coherent detection module (6) is connected to the input end of the dynamic fault classification module (7), and the phase coherent detection module (6) receives the intermediate frequency channel signal and the frequency band energy characteristics to calculate the phase difference between the pressure fluctuation and the vibration and transmits it to the dynamic fault classification module (7); The output end of the dynamic fault classification module (7) is connected to the input end of the communication and display module (9), and the dynamic fault classification module (7) outputs a fault code through logical judgment; The input end of the visual motion verification module (8) is connected to the output end of the photoelectric encoder and the image acquisition unit respectively, and the output end of the visual motion verification module (8) is also connected to the input end of the communication and display module (9). The visual motion verification module (8) verifies the valve action frequency through visual data; The communication and display module (9) is used to receive fault codes and verification results and output graded alarms.

2. The safety valve of an air-conditioning system based on visual assistance according to claim 1, characterized in that, The signal preprocessing module (4) separates the dynamic pressure change into low-frequency, medium-frequency, and high-frequency channel signals and transmits them to the dynamic fault classification module (7) and the phase coherence detection module (6), specifically comprising the following steps: Separate the pressure signal of dynamic pressure changes through a third-order Sallen-Key filter; The low-frequency channel signal adopts a first-order low-pass filter with a frequency range of 0.1 to 2 Hz and a time constant set to 0.8 seconds to detect slow changes in pipeline resistance; The intermediate frequency channel signal is filtered using a second-order bandpass filter with a frequency range of 5 to 20 Hz, a center frequency of 10 Hz, and a quality factor of 0.707 to extract the periodic fluctuations of the regulation circle; The high-frequency channel signal adopts a second-order high-pass filter with a frequency range of 50 to 200 Hz, a center frequency of 50 Hz, and a quality factor of 0.5 to capture the transient impact of spring stiffness.

3. The safety valve of an air conditioning system based on visual assistance according to claim 1, characterized in that, The three-axis vibration sensor (3) extracts the frequency band energy characteristics of the vibration signal, and specifically includes the following steps: Separate the vibration signal through a programmable filter to obtain the low-frequency band energy characteristics and the high-frequency band energy characteristics. The frequency range of the low-frequency band energy characteristics is 5 to 50 Hz, which corresponds to flutter detection, and the frequency range of the high-frequency band energy characteristics is 50 to 200 Hz, which corresponds to frequency jump detection.

4. The safety valve of an air-conditioning system based on visual assistance according to claim 1, wherein The dynamic fault classification module (7) outputs a fault code through logical judgment, and specifically includes the following steps: Based on the baseline tracking circuit in the dynamic fault classification module (7), calculate the pressure baseline in real time and generate a dynamic threshold; In the dynamic fault classification module (7), extract the pressure channel energy, vibration frequency band energy, and phase difference characteristics, and perform weighted fusion; Through the fuzzy decision-making circuit in the dynamic fault classification module (7), determine the fault type in combination with the threshold condition and the membership function.

5. The safety valve of an air-conditioning system based on visual assistance according to claim 4, wherein The method of calculating the pressure baseline in real time and generating a dynamic threshold based on the baseline tracking circuit in the dynamic fault classification module (7) specifically includes the following steps: The baseline tracking circuit in the dynamic fault classification module (7) uses a first-order inertial filter. The current baseline voltage value is 95% of the previous baseline voltage value plus 5% of the current input voltage value; The adaptive threshold circuit in the dynamic fault classification module (7) is implemented by a comparator. The dynamic threshold is the sum of the baseline voltage value and three times the static noise standard deviation, where the static noise standard deviation is determined through static calibration; The parameters of the dynamic threshold are dynamically adjusted through the serial clock pin and data input pin of the digital potentiometer in the dynamic fault classification module (7).

6. The safety valve of an air-conditioning system based on visual assistance according to claim 4, characterized in that The method of extracting the pressure channel energy, vibration frequency band energy, and phase difference characteristics and performing weighted fusion in the dynamic fault classification module (7) specifically includes the following steps: Normalize the input low-frequency channel signal, intermediate-frequency channel signal, high-frequency channel signal, low-frequency band energy characteristics, and high-frequency band energy characteristics; After normalization, each signal is multiplied by a preset weight coefficient and then added to obtain a comprehensive fault score, where the weight of the low-frequency channel signal is 0.3, the weight of the intermediate-frequency channel signal is 0.25, the weight of the high-frequency channel signal is 0.25, the weight of the low-frequency band energy characteristics is 0.1, and the weight of the high-frequency band energy characteristics is 0.

1.

7. The safety valve of an air-conditioning system based on visual assistance according to claim 4, characterized in that The method of determining the fault type by combining the threshold condition and the membership function through the fuzzy decision-making circuit in the dynamic fault classification module (7) specifically includes the following steps: The determination condition for excessive spring stiffness is that the comprehensive fault score exceeds 1.5, and at the same time, the high-frequency channel signal exceeds three times its static standard deviation, and the phase difference between pressure and vibration is greater than 60 degrees; The determination condition for improper adjustment ring position is that the intermediate-frequency channel signal exceeds twice its static standard deviation, and the ratio of the peak-to-peak value to the mean value of the pressure fluctuation is greater than 0.4; The determination condition for excessive pipeline resistance is that the low-frequency channel signal exceeds 2.5 times its static standard deviation, and the change rate of the baseline voltage exceeds 0.05 V per second.

8. The safety valve of an air-conditioning system based on visual assistance according to claim 1, characterized in that The visual action verification module (8) verifies the valve action frequency through visual data, and specifically includes the following steps: The optoelectronic encoder captures the rising edge of the optoelectronic pulse to detect transient action anomalies, and the valve action frequency is the number of rising edges of the optoelectronic pulse; The camera captures images, calculates the displacement trend through the frame difference method. The displacement change amount is the average value of the pixel gray value differences between two adjacent frames of images. The threshold is set to 20 gray levels per frame. If the displacement trend exceeds 20 gray levels per frame, it is determined as a valid action; Calculate the action frequency according to the number of valid actions / total number of frames * time interval between two adjacent frames. If the valve action frequency - action frequency < 0.2 * valve action frequency, the output result is that the verification passes.

9. The safety valve of an air-conditioning system based on visual assistance according to claim 1, wherein, The communication and display module (9) is used to receive the fault code and verification result and output a hierarchical alarm, which specifically includes the following steps: Receive the fault type output by the dynamic fault classification module (7) and receive the output result of the visual action verification module (8) as the verification passes, then transmit information externally and alarm.

Images