Fault diagnosis method for energy-saving low-temperature pulse vacuum drier

Abstract

The invention relates to the technical field of drying equipment fault diagnosis, and discloses an energy-saving low-temperature pulse vacuum dryer fault diagnosis method, which comprises the following steps: acquiring key characteristic data in the operation process of a dryer through multiple sensors; cleaning and normalizing the acquired data to remove noise and abnormal values; extracting feature data based on the processed data; identifying possible fault categories by using the fault classification model; and dynamically adjusting the fault priority and confirming the fault. Compared with the prior art, the technical problems that in complex operation conditions, especially in low-temperature, pulse drying and high-humidity environments, internal temperature distribution of the drying machine, vacuum system leakage, abnormal humidity or uneven airflow cannot be accurately recognized, and efficient fault diagnosis is difficult to achieve are solved. According to the method, accurate classification of complex faults is realized by combining multivariable data feature extraction and a dynamic priority fault diagnosis method, and the accuracy and efficiency of fault diagnosis are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of drying equipment fault diagnosis, and in particular relates to an energy-saving low-temperature pulse vacuum drying machine fault diagnosis method. Background Art

[0002] At present, during the operation of energy-saving low-temperature pulse vacuum dryers, the accuracy and efficiency of fault diagnosis are still insufficient due to the complex coupling of multivariable parameters such as temperature, humidity, vacuum pressure and airflow. For example, most of the existing technologies rely on a single parameter for fault analysis and cannot fully capture the dynamic characteristics of the dryer's operating status. Especially under low temperature, high humidity or pulse airflow conditions, problems such as fault detection lag and high misjudgment rate are prone to occur, which seriously affect the operating efficiency and product quality of the dryer. The existing technology cannot fully meet the needs of fast and accurate diagnosis of multi-dimensional faults under complex operating conditions. Therefore, there is an urgent need for a method that can achieve accurate extraction of multivariate features and dynamic fault priority diagnosis under complex conditions such as low temperature, high humidity, and pulse vacuum, so as to improve the operating reliability and diagnostic efficiency of the dryer. Summary of the invention

[0003] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to propose an energy-saving low-temperature pulse vacuum dryer fault diagnosis method, which aims to solve the technical problem that the prior art cannot accurately identify the internal temperature distribution of the dryer, vacuum system leakage, humidity abnormality or uneven airflow under complex operating conditions, especially in low temperature, pulse drying and high humidity environments, and it is difficult to achieve efficient fault diagnosis.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides an energy-saving low-temperature pulse vacuum dryer fault diagnosis method,

[0005] The energy-saving low-temperature pulse vacuum dryer fault diagnosis method comprises:

[0006] Step S10: extract key characteristic data during the operation of the energy-saving low-temperature pulse vacuum dryer, including: temperature matrix T(t): the temperature distribution at time t recorded by M temperature sensors arranged in the cavity of the energy-saving low-temperature pulse vacuum dryer, T(t) = [t1, ..., t j , ..., t m ], where t j Represents the temperature value of the jth sensor at time t; m is the number of temperature sensors; vacuum pressure deviation ΔP(t): The vacuum pressure P of the current energy-saving low-temperature pulse vacuum dryer is obtained through the vacuum pressure sensor current (t), and calculate its difference with the preset dynamic reference pressure P baseline(t) vacuum pressure deviation ΔP(t); humidity sequence H(t): the water vapor concentration distribution at time t in the energy-saving low-temperature pulse vacuum dryer cavity is collected by humidity sensor; pulse airflow characteristics Q(t): the instantaneous pulse airflow flow q(t) and pulse frequency f are collected by dynamic airflow sensor p (t) and calculate the pulse airflow characteristics Q(t);

[0007] Step S20: performing data cleaning and normalization processing on the key feature data at time t collected in step S10, specifically including:

[0008] The key characteristic data are smoothed by a Kalman filter to filter out random fluctuations, and the first standard threshold range, the second standard threshold range, the third standard threshold range and the fourth standard threshold range are set. According to the first, second, third and fourth standard threshold ranges, the temperature matrix T(t), the vacuum pressure deviation ΔP(t), the humidity sequence H(t) and the pulse airflow characteristic Q(t) are respectively subjected to outlier elimination processing to obtain the key characteristic data after cleaning;

[0009] Normalizing the key characteristic data after cleaning to obtain second key characteristic data, the second key characteristic data includes a temperature matrix T2(t), a vacuum pressure deviation ΔP2(t), a humidity sequence H2(t) and a pulse airflow characteristic Q2(t);

[0010] Step S30: Extract dryer fault feature data from the second key feature data, including temperature gradient feature G T , Pulse airflow energy characteristics E Q , humidity gradient characteristics G P and vacuum pressure deviation gradient characteristic G H ;

[0011] Step S40: using the extracted dryer fault feature data and the second key feature data, a dryer fault classification model is used to make a preliminary diagnosis of the fault; wherein the input of the dryer fault classification model is X(t)=[G T ,G H ,G P ,E Q ,T2(t),ΔP2(t),H2(t),Q2(t)]; The output of the dryer fault classification model includes four categories: “Probability P1; Category 1; Temperature anomaly;”, “Probability P2; Category 2: Vacuum leak;”, “Probability P3; Category 3: Humidity anomaly;” and “Probability P4; Category 4: Insufficient airflow”;

[0012] Step S50: Obtain the historical occurrence frequency f of the i-th type of fault i , combined with the probability P of the i-th type of fault occurring from the output of the dryer fault classification model in step S40i , dynamically adjust the fault priority to obtain the comprehensive weight w of the i-th fault i ; According to the comprehensive weight w i Sort the fault categories in ascending order, and further confirm the faults in order of comprehensive weight from high to low.

[0013] Preferably, in step S10, the calculation formula of the vacuum pressure deviation ΔP(t) is:

[0014] Preferably, in step S10, the calculation formula of the pulse airflow characteristic Q(t) is:

[0015]

[0016] Among them, Pulse() is the pulse characteristic function.

[0017] Preferably, in step S30, the temperature gradient characteristic G T The calculation formula is:

[0018]

[0019] Where Δx is the distance between adjacent sensors.

[0020] Preferably, in step S30, the pulse airflow energy E Q The calculation formula is

[0021] Preferably, in step S50, the formula for dynamically adjusting the fault priority is:

[0022] w i =α·f i +(1-α)·P i

[0023] Among them, w i is the comprehensive weight of the i-th type of fault; α is the preset historical weight coefficient, which is used to balance the impact of historical data and current diagnosis results.

[0024] Preferably, in step S40, the formula of the dryer fault classification model is:

[0025] y=σ(W·Conv(X(t))+b)

[0026] Among them, Conv(X(t)) is a temporal convolution operation on the input, which is used to extract dynamic change patterns; W is the weight matrix of the dryer fault classification model; b is the bias term of the dryer fault classification model; σ is an activation function used to map the output value to the classification probability; y is the output of the dryer fault classification model.

[0027] The present invention also provides an energy-saving low-temperature pulse vacuum dryer fault diagnosis system comprising:

[0028] The data acquisition module is used to extract key characteristic data during the operation of the energy-saving low-temperature pulse vacuum dryer, including: temperature matrix T(t): the temperature distribution at time t is recorded by M temperature sensors arranged in the cavity of the energy-saving low-temperature pulse vacuum dryer, T(t) = [t1, ..., t j , ..., t m ], where t j Represents the temperature value of the jth sensor at time t; m is the number of temperature sensors; vacuum pressure deviation ΔP(t): The vacuum pressure P of the current energy-saving low-temperature pulse vacuum dryer is obtained through the vacuum pressure sensor current (t), and calculate its difference with the preset dynamic reference pressure P baseline (t) vacuum pressure deviation ΔP(t); humidity sequence H(t): the water vapor concentration distribution at time t in the energy-saving low-temperature pulse vacuum dryer cavity is collected by humidity sensor; pulse airflow characteristics Q(t): the instantaneous pulse airflow flow q(t) and pulse frequency f are collected by dynamic airflow sensor p (t) and calculate the pulse airflow characteristics Q(t);

[0029] The data cleaning and normalization module is used to perform data cleaning and normalization processing on the key feature data at time t collected in step S10, specifically including:

[0030] The key characteristic data are smoothed by a Kalman filter to filter out random fluctuations, and the first standard threshold range, the second standard threshold range, the third standard threshold range and the fourth standard threshold range are set. According to the first, second, third and fourth standard threshold ranges, the temperature matrix T(t), the vacuum pressure deviation ΔP(t), the humidity sequence H(t) and the pulse airflow characteristic Q(t) are respectively subjected to outlier elimination processing to obtain the key characteristic data after cleaning;

[0031] Normalizing the key characteristic data after cleaning to obtain second key characteristic data, the second key characteristic data includes a temperature matrix T2(t), a vacuum pressure deviation ΔP2(t), a humidity sequence H2(t) and a pulse airflow characteristic Q2(t);

[0032] A feature extraction module is used to extract dryer fault feature data from the second key feature data, including the temperature gradient feature G T , Pulse airflow energy characteristics E Q , humidity gradient characteristics G P and vacuum pressure deviation gradient characteristic G H ;

[0033] The fault classification module is used to use the extracted dryer fault feature data and the second key feature data to perform preliminary diagnosis of the fault through the dryer fault classification model; wherein the input of the dryer fault classification model is X(t)=[G T ,G H ,G P ,E Q ,T2(t),ΔP2(t),H2(t),Q2(t)]; The output of the dryer fault classification model includes four categories: “Probability P1; Category 1; Temperature anomaly;”, “Probability P2; Category 2: Vacuum leak;”, “Probability P3; Category 3: Humidity anomaly;” and “Probability P4; Category 4: Insufficient airflow”;

[0034] Dynamic priority adjustment module, used to obtain the historical occurrence frequency f of the i-th type of fault i , combined with the probability P of the i-th type of fault occurring from the output of the dryer fault classification model in step S40 i , dynamically adjust the fault priority to obtain the comprehensive weight w of the i-th fault i ; According to the comprehensive weight w i Sort the fault categories in ascending order, and further confirm the faults in order of comprehensive weight from high to low.

[0035] The present invention also provides an energy-saving low-temperature pulse vacuum dryer fault diagnosis device, comprising a memory, a processor, and an energy-saving low-temperature pulse vacuum dryer fault diagnosis program stored in the memory and executable on the processor. When the energy-saving low-temperature pulse vacuum dryer fault diagnosis program is executed by the processor, the energy-saving low-temperature pulse vacuum dryer fault diagnosis method is implemented.

[0036] The present invention also provides a computer program product, including an energy-saving low-temperature pulse vacuum dryer fault diagnosis program, which implements the energy-saving low-temperature pulse vacuum dryer fault diagnosis method when executed by a processor.

[0037] The beneficial effect of the present invention is that compared with the technical problem in the prior art that under complex operating conditions, especially under low temperature, pulse drying and high humidity environments, the internal temperature distribution of the dryer, vacuum system leakage, humidity abnormalities or uneven airflow cannot be accurately identified, and efficient fault diagnosis is difficult to achieve, this application combines multivariate data feature extraction and dynamic priority fault diagnosis methods to achieve accurate classification of complex faults and improve the accuracy and efficiency of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 The figure is a flow chart of a first embodiment of a method for diagnosing faults of an energy-saving low-temperature pulse vacuum dryer according to the present invention.

[0040] Figure 2 The present invention is a schematic diagram of an energy-saving low-temperature pulse vacuum dryer fault diagnosis method. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Embodiment 1: Figure 1 , which is a flow chart of the first embodiment of the energy-saving low-temperature pulse vacuum dryer fault diagnosis method of the present invention, and proposes the first embodiment of the energy-saving low-temperature pulse vacuum dryer fault diagnosis method of the present invention.

[0043] In the first embodiment, the energy-saving low-temperature pulse vacuum dryer fault diagnosis method includes:

[0044] Step S10: extract key characteristic data during the operation of the energy-saving low-temperature pulse vacuum dryer, including: temperature matrix T(t): the temperature distribution at time t recorded by M temperature sensors arranged in the cavity of the energy-saving low-temperature pulse vacuum dryer, T(t) = [t1, ..., t j , ..., t m ], where t j Represents the temperature value of the jth sensor at time t; m is the number of temperature sensors; vacuum pressure deviation ΔP(t): The vacuum pressure P of the current energy-saving low-temperature pulse vacuum dryer is obtained through the vacuum pressure sensor current (t), and calculate its difference with the preset dynamic reference pressure P baseline (t) vacuum pressure deviation ΔP(t); humidity sequence H(t): the water vapor concentration distribution at time t in the energy-saving low-temperature pulse vacuum dryer cavity is collected by humidity sensor; pulse airflow characteristics Q(t): the instantaneous pulse airflow flow q(t) and pulse frequency f are collected by dynamic airflow sensorp (t) and calculate the pulse airflow characteristics Q(t);

[0045] It should be noted that through the combination of the temperature sensor matrix, vacuum pressure sensor, and airflow sensor, the temperature distribution, pressure fluctuations and airflow characteristics inside the drying chamber can be recorded in real time. Through the precise collection of multi-dimensional parameters, a comprehensive evaluation of the equipment's operating status is ensured, avoiding the possibility of diagnostic errors due to abnormalities in a single parameter.

[0046] Step S20: performing data cleaning and normalization processing on the key feature data at time t collected in step S10, specifically including:

[0047] The key characteristic data are smoothed by a Kalman filter to filter out random fluctuations, and the first standard threshold range, the second standard threshold range, the third standard threshold range and the fourth standard threshold range are set. According to the first, second, third and fourth standard threshold ranges, the temperature matrix T(t), the vacuum pressure deviation ΔP(t), the humidity sequence H(t) and the pulse airflow characteristic Q(t) are respectively subjected to outlier elimination processing to obtain the key characteristic data after cleaning;

[0048] Normalizing the key characteristic data after cleaning to obtain second key characteristic data, the second key characteristic data includes a temperature matrix T2(t), a vacuum pressure deviation ΔP2(t), a humidity sequence H2(t) and a pulse airflow characteristic Q2(t);

[0049] It should be noted that the smoothing of key feature data by the Kalman filter significantly reduces the impact of random fluctuations caused by changes in the external environment or sensor errors, and improves the stability and reliability of the key feature data; the set multiple standard threshold ranges (the first to fourth threshold ranges) can accurately capture the effective range of feature data, eliminate abnormal values ​​that exceed the range, and reduce the interference of error accumulation on subsequent analysis, thereby effectively optimizing the accuracy of key feature extraction; normalization is performed after data cleaning so that each key feature data has a unified numerical scale, which helps to improve the computational efficiency and accuracy of subsequent algorithm processing, and enhances the stability of the system in multivariate collaborative analysis; the implementation of the above steps effectively reduces the impact of data anomalies on system performance, improves the adaptability of the overall system in complex environments, ensures the availability and consistency of key feature data processing results, and provides high-quality data support for subsequent analysis and control links.

[0050] Step S30: Extract dryer fault feature data from the second key feature data, including temperature gradient feature G T , Pulse airflow energy characteristics E Q , humidity gradient characteristics G Pand vacuum pressure deviation gradient characteristic G H ;

[0051] It should be noted that by extracting key feature data, the operating status of the dryer can be characterized from multiple dimensions, and potential abnormalities of the equipment can be captured from the perspectives of temperature changes, airflow fluctuations, pressure changes, etc., providing accurate, reliable and efficient technical support for real-time monitoring and fault diagnosis of the dryer operating status. This method not only improves the comprehensiveness and accuracy of the diagnosis, but also enhances the robustness and stability of the system, ultimately providing a guarantee for equipment maintenance and fault prevention.

[0052] Step S40: using the extracted dryer fault feature data and the second key feature data, a dryer fault classification model is used to make a preliminary diagnosis of the fault; wherein the input of the dryer fault classification model is X(t)=[G T ,G H ,G P ,E Q ,T2(t),ΔP2(t),H2(t),Q2(t)]; The output of the dryer fault classification model includes four categories: “Probability P1; Category 1; Temperature anomaly;”, “Probability P2; Category 2: Vacuum leak;”, “Probability P3; Category 3: Humidity anomaly;” and “Probability P4; Category 4: Insufficient airflow”;

[0053] It should be noted that the technical effect of the dryer fault classification model is not only to identify the fault category, but also to improve the accuracy and real-time performance of the diagnosis. By integrating multi-dimensional key feature data such as temperature, humidity, and airflow, the classification model can accurately capture subtle abnormal changes in complex environments and reduce possible interference between features. Through the quantification of probability, the diagnostic results are clearly interpretable and efficient, which facilitates subsequent fault handling and decision optimization.

[0054] For example, in actual applications, if the dryer temperature sensor detects that the temperature matrix fluctuates abnormally during operation, and at the same time the vacuum pressure deviation increases and the humidity sequence becomes unstable, and the airflow characteristics also show a downward trend, after classification model analysis, the system output category 2 is the main fault mode, indicating that the dryer may have a vacuum leakage problem. Maintenance personnel can take targeted repair measures based on this to reduce the impact of equipment failure on production.

[0055] Step S50: Obtain the historical occurrence frequency f of the i-th type of fault i , combined with the probability P of the i-th type of fault occurring from the output of the dryer fault classification model in step S40 i , dynamically adjust the fault priority to obtain the comprehensive weight w of the i-th fault i ; According to the comprehensive weight w iSort the fault categories in ascending order, and further confirm the faults in order of comprehensive weight from high to low.

[0056] It should be noted that the formula for dynamically adjusting the fault priority is:

[0057] w i =α·f i +(1-α)·P i

[0058] Among them, w i is the comprehensive weight of the i-th type of fault; α is the preset historical weight coefficient, which is used to balance the influence of historical data and current diagnosis results

[0059] It should be understood that by introducing the weight parameter α to dynamically balance the impact of historical trends and current diagnostic results, we can retain the guiding role of historical experience while taking into account the real-time changes of the current state; give priority to high-weighted fault categories, reduce the interference of low-risk faults on diagnostic resources, avoid the deviations that may be caused by relying solely on real-time data or historical data, and enhance the stability and adaptability of diagnosis.

[0060] For example, the historical frequency of dryer failures f i and real-time diagnosis probability P i As follows: Category 1 (temperature abnormality), f1=0.7, P1=0.3; Category 2 (vacuum leakage), f2=0.5, P2=0.6; Category 3 (humidity abnormality), f3=0.4, P3=0.8; Category 4 (insufficient airflow), f4=0.3, P4=0.2, weight coefficient α=0.6; the priority after calculating the comprehensive weight ranking is: Category 3 (humidity abnormality)> Category 1 (temperature abnormality)> Category 2 (vacuum leakage)> Category 4 (insufficient airflow). Based on this result, maintenance personnel can give priority to humidity abnormality and temperature abnormality, so as to quickly focus on the possible causes of the fault.

[0061] In addition, the energy-saving low-temperature pulse vacuum dryer fault diagnosis system provided by the present invention adopts an energy-saving low-temperature pulse vacuum dryer fault diagnosis method in the above embodiment, which can solve the technical problem of energy-saving low-temperature pulse vacuum dryer fault diagnosis. Compared with the prior art, the beneficial effect of the energy-saving low-temperature pulse vacuum dryer fault diagnosis system provided by the present invention is the same as the beneficial effect of the energy-saving low-temperature pulse vacuum dryer fault diagnosis method provided by the above embodiment, and the other technical features of the energy-saving low-temperature pulse vacuum dryer fault diagnosis system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0062] The present invention provides an energy-saving low-temperature pulse vacuum dryer fault diagnosis device, please refer to Figure 2, an energy-saving low-temperature pulse vacuum dryer fault diagnosis device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor so that at least one processor can execute an energy-saving low-temperature pulse vacuum dryer fault diagnosis method in the above-mentioned embodiment 1. An energy-saving low-temperature pulse vacuum dryer fault diagnosis device in the embodiment of the present invention may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. An energy-saving low-temperature pulse vacuum dryer fault diagnosis device is only an example and should not bring any limitations to the functions and scope of use of the embodiments of the present invention. An energy-saving low-temperature pulse vacuum dryer fault diagnosis device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of an energy-saving low-temperature pulse vacuum dryer fault diagnosis device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow an energy-saving low-temperature pulse vacuum dryer fault diagnosis device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an energy-saving low-temperature pulse vacuum dryer fault diagnosis device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0063] The present invention also provides a computer program product, including a computer program, which implements the steps of the above-mentioned energy-saving low-temperature pulse vacuum dryer fault diagnosis method when executed by a processor. The computer program product provided by the present invention can solve the technical problem of energy-saving low-temperature pulse vacuum dryer fault diagnosis. Compared with the prior art, the beneficial effects of the computer program product provided by the present invention are the same as the beneficial effects of the energy-saving low-temperature pulse vacuum dryer fault diagnosis method provided by the above-mentioned embodiment, which will not be repeated here.

[0064] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present invention are executed.

[0065] It should be understood that the various parts disclosed in the present invention can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0066] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for diagnosing faults of an energy-saving low-temperature pulse vacuum dryer, characterized in that: Methods include: Step S10: extract key characteristic data during the operation of the energy-saving low-temperature pulse vacuum dryer, including: temperature matrix T(t): the temperature distribution at time t recorded by M temperature sensors arranged in the cavity of the energy-saving low-temperature pulse vacuum dryer, T(t) = [t1, ..., t j , ..., t m ], where t j Represents the temperature value of the jth sensor at time t; m is the number of temperature sensors; vacuum pressure deviation ΔP(t): The vacuum pressure P of the current energy-saving low-temperature pulse vacuum dryer is obtained through the vacuum pressure sensor current (t), and calculate its difference with the preset dynamic reference pressure P baseline (t) vacuum pressure deviation ΔP(t); humidity sequence H(t): the water vapor concentration distribution in the energy-saving low-temperature pulse vacuum dryer cavity at time t is collected by the humidity sensor; pulse airflow characteristics Q(t): the instantaneous pulse airflow flow q(t) and pulse frequency fp(t) are collected by the dynamic airflow sensor and the pulse airflow characteristics Q(t) are calculated; Step S20: performing data cleaning and normalization processing on the key feature data at time t collected in step S10, specifically including: The key characteristic data are smoothed by a Kalman filter to filter out random fluctuations, and the first standard threshold range, the second standard threshold range, the third standard threshold range and the fourth standard threshold range are set. According to the first, second, third and fourth standard threshold ranges, the temperature matrix T(t), the vacuum pressure deviation ΔP(t), the humidity sequence H(t) and the pulse airflow characteristic Q(t) are respectively subjected to outlier elimination processing to obtain the key characteristic data after cleaning; Normalizing the key characteristic data after cleaning to obtain second key characteristic data, the second key characteristic data includes a temperature matrix T2(t), a vacuum pressure deviation ΔP2(t), a humidity sequence H2(t) and a pulse airflow characteristic Q2(t); Step S30: Extract dryer fault feature data from the second key feature data, including temperature gradient feature G T , Pulse airflow energy characteristics E Q , humidity gradient characteristics G P and vacuum pressure deviation gradient characteristic G H ; Step S40: using the extracted dryer fault feature data and the second key feature data, a dryer fault classification model is used to make a preliminary diagnosis of the fault; wherein the input of the dryer fault classification model is X(t)=[G T , G H , G P , E Q , T2(t), ΔP2(t), H2(t), Q2(t)]; The output of the dryer fault classification model includes four categories: "Probability P1; Category 1; Temperature anomaly;", "Probability P2; Category 2: Vacuum leak;", "Probability P3; Category 3: Humidity anomaly;" and "Probability P4; Category 4: Insufficient airflow"; Step S50: Obtain the historical occurrence frequency f of the i-th type of fault i , combined with the probability P of the i-th type of fault output by the dryer fault classification model in step S40 i , dynamically adjust the fault priority to obtain the comprehensive weight w of the i-th fault j ; According to the comprehensive weight w i Sort the fault categories in ascending order, and further confirm the faults in order of comprehensive weight from high to low.

2. The energy-saving low-temperature pulse vacuum dryer fault diagnosis method according to claim 1, characterized in that: In step S10, the calculation formula of vacuum pressure deviation AP(t) is:

3. The energy-saving low-temperature pulse vacuum dryer fault diagnosis method according to claim 1, characterized in that: In step S10, the calculation formula of the pulse airflow characteristic Q(t) is: Among them, Pulse() is the pulse characteristic function.

4. The energy-saving low-temperature pulse vacuum dryer fault diagnosis method according to claim 1, characterized in that: In step S30, the temperature gradient characteristic G T The calculation formula is: Where Δx is the distance between adjacent sensors.

5. The energy-saving low-temperature pulse vacuum dryer fault diagnosis method according to claim 1, characterized in that: In step S30, the pulse airflow energy E Q The calculation formula is 6. The energy-saving low-temperature pulse vacuum dryer fault diagnosis method according to claim 1, characterized in that: In step S50, the formula for dynamically adjusting the fault priority is: w i =α·f i +(1-a)·P i Among them, w i is the comprehensive weight of the i-th type of fault; α is the preset historical weight coefficient, which is used to balance the impact of historical data and current diagnosis results.

7. The energy-saving low-temperature pulse vacuum dryer fault diagnosis method according to claim 1, characterized in that: In step S40, the formula of the dryer fault classification model is: y=σ(W·Conv(X(t))+b) Among them, Conv(X(t)) is a temporal convolution operation on the input, which is used to extract dynamic change patterns; W is the weight matrix of the dryer fault classification model; b is the bias term of the dryer fault classification model; σ is an activation function used to map the output value to the classification probability; y is the output of the dryer fault classification model.

8. An energy-saving low-temperature pulse vacuum dryer fault diagnosis system, characterized in that: The energy-saving low-temperature pulse vacuum dryer fault diagnosis system comprises: The data acquisition module is used to extract key characteristic data during the operation of the energy-saving low-temperature pulse vacuum dryer, including: temperature matrix T(t): the temperature distribution at time t is recorded by M temperature sensors arranged in the cavity of the energy-saving low-temperature pulse vacuum dryer, T(t) = [t1, ..., t j , ..., t m ], where t j Represents the temperature value of the jth sensor at time t; m is the number of temperature sensors; vacuum pressure deviation AP(t): obtain the vacuum pressure P of the current energy-saving low-temperature pulse vacuum dryer through the vacuum pressure sensor current (t), and calculate its difference with the preset dynamic reference pressure P baseline (t) vacuum pressure deviation AP(t); humidity sequence H(t): the water vapor concentration distribution in the energy-saving low-temperature pulse vacuum dryer cavity at time t is collected by the humidity sensor; pulse airflow characteristics Q(t): the instantaneous pulse airflow flow q(t) and pulse frequency fp(t) are collected by the dynamic airflow sensor and the pulse airflow characteristics Q(t) are calculated; The data cleaning and normalization module is used to perform data cleaning and normalization processing on the key feature data at time t collected in step S10, specifically including: The key characteristic data are smoothed by a Kalman filter to filter out random fluctuations, and the first standard threshold range, the second standard threshold range, the third standard threshold range and the fourth standard threshold range are set. According to the first, second, third and fourth standard threshold ranges, the temperature matrix T(t), the vacuum pressure deviation AP(t), the humidity sequence H(t) and the pulse airflow characteristic Q(t) are respectively subjected to outlier elimination processing to obtain the key characteristic data after cleaning; Normalizing the key characteristic data after cleaning to obtain second key characteristic data, the second key characteristic data includes a temperature matrix T2(t), a vacuum pressure deviation ΔP2(t), a humidity sequence H2(t) and a pulse airflow characteristic Q2(t); A feature extraction module is used to extract dryer fault feature data from the second key feature data, including the temperature gradient feature G T , Pulse airflow energy characteristics E Q , humidity gradient characteristics G P and vacuum pressure deviation gradient characteristic G H ; The fault classification module is used to use the extracted dryer fault feature data and the second key feature data to perform preliminary diagnosis of the fault through the dryer fault classification model; wherein the input of the dryer fault classification model is X(t)=[G T , G H , G P , E Q , T2(t), ΔP2(t), H2(t), Q2(t)]; The output of the dryer fault classification model includes four categories: "Probability P1; Category 1; Temperature anomaly;", "Probability P2; Category 2: Vacuum leak;", "Probability P3; Category 3: Humidity anomaly;" and "Probability P4; Category 4: Insufficient airflow"; Dynamic priority adjustment module, used to obtain the historical occurrence frequency f of the i-th type of fault i , combined with the probability P of the i-th type of fault occurring from the output of the dryer fault classification model in step S40 i , dynamically adjust the fault priority to obtain the comprehensive weight w of the i-th fault j ; According to the comprehensive weight w i Sort the fault categories in ascending order, and further confirm the faults in order of comprehensive weight from high to low.

9. An energy-saving low-temperature pulse vacuum dryer fault diagnosis device, characterized in that: The energy-saving low-temperature pulse vacuum dryer fault diagnosis device comprises: a memory, a processor, and an energy-saving low-temperature pulse vacuum dryer fault diagnosis program stored in the memory and executable on the processor. When the energy-saving low-temperature pulse vacuum dryer fault diagnosis program is executed by the processor, the energy-saving low-temperature pulse vacuum dryer fault diagnosis method described in any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The computer program product includes an energy-saving low-temperature pulse vacuum dryer fault diagnosis program, which, when executed by a processor, implements the energy-saving low-temperature pulse vacuum dryer fault diagnosis method described in any one of claims 1 to 7.

Images