Chemical raw material grinding equipment and fault detection method

Abstract

The invention relates to the technical field of smashing and grinding treatment, in particular to chemical raw material grinding equipment and a fault detection method.The method comprises the steps that a target sequence segment is screened out according to the abnormal degree of a motor vibration data time sequence; based on a plurality of data of the motor and the grinding bin body in the operation process, obtaining interference time delay of the target sequence segment to vibration data of each motor, further calculating the probability that vibration of the motor is interfered by vibration of the grinding bin body, and obtaining a main target sequence segment from the target sequence segment; analyzing the motor vibration data in the main target sequence segment to obtain a fault component; according to the interference of each fault component on the grinding bin body, the severity of each fault component is obtained, and then a fault detection result is obtained. The probability that the vibration data of the motor is interfered by the vibration of the grinding bin body is obtained according to the correlation between the vibration data of different positions of the grinding bin body and the vibration data of the motor, and then the accuracy of motor fault detection is improved.

Description

Technical Field

[0001] The invention relates to the technical field of crushing and grinding processing, and in particular to grinding equipment for chemical raw materials and a fault detection method. Background Art

[0002] Chemical raw materials are widely used in the chemical industry. They are the basis for manufacturing various chemical products. Grinding is a crucial link in the production and processing of chemical raw materials. Grinding equipment improves the utilization rate of raw materials and the quality of products by crushing, mixing and homogenizing raw materials. The motor of the grinding equipment is a core component, and its operating status directly affects the performance and production efficiency of the entire equipment. Fault detection of the motor of the grinding equipment can improve the safety and stability of the equipment operation and ensure grinding efficiency.

[0003] In the prior art CN118310625B (a robot servo drive fault monitoring method and system), fault identification is performed by analyzing the resonance phenomenon between different vibration data. This method often uses a vibration sensor to obtain the vibration data of the motor, and then analyzes the motor vibration data. When the motor vibration data fluctuates abnormally, it is considered that the motor is faulty. However, when the grinding equipment is working, the grinding chamber will produce complex vibration phenomena when grinding chemical raw materials, which will interfere with the vibration data of the motor. This interference is not only caused by the resonance effect, but also by other complex vibration frequencies. This vibration interference will reduce the accuracy of motor fault identification. Summary of the invention

[0004] The invention provides a grinding device for chemical raw materials and a fault detection method to solve the existing problems.

[0005] A method for detecting grinding faults of chemical raw materials of the present invention adopts the following technical scheme: An embodiment of the present invention provides a method for detecting grinding faults of chemical raw materials, the method comprising the following steps: Acquire several data of the motor and the grinding chamber during operation; the several data are vibration frequency data obtained by using a vibration sensor, and the distances from different positions of the grinding chamber to the motor; the vibration frequency data includes a chamber vibration data time series and a motor vibration data time series; According to the abnormal degree of the motor vibration data time series, a target sequence segment is screened out; the position of the grinding chamber body closest to the motor is taken as the reference position, and the average difference between the corresponding time of the adjacent target data closest to the motor vibration data and the acquisition time of the motor vibration data is obtained as the interference delay of the target sequence segment to each motor vibration data, the target data is the vibration data of the grinding chamber body when the difference in the change rate between the target sequence segment and the vibration data of the grinding chamber body at the reference position is less than a preset threshold, and the probability that the motor vibration is interfered by the vibration of the grinding chamber body is further calculated, and the probability is positively correlated with the interference delay of the grinding chamber body to each motor vibration data in the target sequence segment, and negatively correlated with the vibration data of the grinding chamber body at the time before the corresponding interference delay of the motor vibration data at the reference position causing interference to the motor vibration data in the target sequence segment, and the main target sequence segment is obtained from the target sequence segment; the motor vibration data in the main target sequence segment is analyzed to obtain the fault component; According to the interference of each fault component on the grinding chamber body, the severity of each fault component is obtained, and then the fault detection result is obtained.

[0006] Furthermore, the method of selecting the target sequence segment according to the abnormality of the motor vibration data time series includes the following specific methods: The motor vibration data time series is equally divided into several sequence segments, and each sequence segment is subjected to fast Fourier transform to obtain the vibration energy values ​​and spectra corresponding to the several sequence segments; the frequency component with the largest amplitude in the spectrum of each sequence segment is obtained as the main frequency of the sequence segment, which is recorded as ; Preset the frequency bandwidth range of the sequence segment according to the main frequency of each sequence segment; According to the vibration energy value and frequency bandwidth range corresponding to each sequence segment, the abnormality degree of the sequence segment is calculated; Preset Threshold , the sequence segments whose abnormality is greater than or equal to the preset threshold are recorded as target sequence segments.

[0007] Furthermore, the abnormality degree of the sequence segment is calculated according to the vibration energy value and frequency bandwidth range corresponding to each sequence segment, including the specific method of: in, Indicates The degree of abnormality of each sequence segment; Indicates the number of all sequence segments in the motor vibration data time series; Indicates The number of data contained in each sequence segment; Indicates In the sequence segment The vibration energy value corresponding to each position; Indicates that except The first sequence segment outside In the sequence segment The vibration energy value corresponding to each position; Indicates the preset The sum of all vibration energy values ​​within the frequency bandwidth of a sequence segment; Represents the sum of all vibration energy values ​​within the frequency bandwidth of all sequence segments; Indicates the absolute value symbol; represents an exponential function with a natural constant as base; Represents the normalization function.

[0008] Furthermore, the specific method for obtaining the interference delay of the target sequence segment on each motor vibration data is as follows: Use the least squares method to fit all motor vibration data in each target sequence segment to obtain the slope of each motor vibration data on the fitting curve; calculate the difference between the slope of the data in the target sequence segment on the fitting curve and the slope corresponding to the vibration data of the grinding chamber at the reference position, and preset the threshold , recording the vibration data of the grinding chamber corresponding to the difference being less than a preset threshold as target data; Among all the target data corresponding to the motor vibration data, the difference between the time corresponding to the previous target data closest to the motor vibration data and the acquisition time of the motor vibration data is used as the reference delay of the motor vibration data. The average of the reference delays of all motor vibration data in the target sequence segment is used as the interference delay of the vibration of the grinding chamber body on the motor vibration data.

[0009] Furthermore, the specific method of calculating the probability that the motor vibration is disturbed by the grinding chamber vibration is as follows: in, Indicates The probability that the motor vibration of a target sequence segment is disturbed by the vibration of the grinding chamber; Indicates The degree of abnormality of the target sequence segment; Indicates The number of motor vibration data in the target sequence segment; Indicates The first Motor vibration data; Indicates that for the reference position The first The motor vibration data is delayed during the interference The corresponding grinding chamber vibration data; Indicates Pearson correlation coefficient between the motor vibration data of the target sequence segment and the grinding chamber vibration data of the reference position; Indicates the vibration of the grinding chamber The interference delay of each motor vibration data in the target sequence segment; Indicates the absolute value symbol; Represents an exponential function with a natural constant as its base.

[0010] Furthermore, the method of obtaining the main target sequence segment from the target sequence segment includes: presetting a threshold , when the probability that the motor vibration data of the target sequence segment is disturbed by the warehouse vibration data is greater than the threshold When the probability that the motor vibration data of the target sequence segment is disturbed by the warehouse vibration data is less than or equal to the threshold , the target sequence segment is marked as the main target sequence segment.

[0011] Furthermore, the motor vibration data in the main target sequence segment is analyzed to obtain the fault component, including the following specific methods: According to the difference in vibration energy values ​​between each vibration frequency and other vibration frequencies, combined with the probability that the motor vibration is disturbed by the grinding chamber vibration, the possibility that the vibration frequency in the main target sequence segment is a fault component is calculated; The first The vibration frequency with the greatest possibility of fault component in the main target sequence segment is recorded as the fault component.

[0012] Furthermore, the method of calculating the possibility that the vibration frequency in the main target sequence segment is a fault component includes the following specific methods: in, Indicates The first The possibility that a vibration frequency is a fault component; Indicates The first The probability that the motor vibration data of the main target sequence segment where the vibration frequency is located is interfered by the grinding chamber vibration data; Indicates The first The vibration energy value corresponding to each vibration frequency; Indicates In the main target sequence segments, except The vibration frequency other than The vibration energy value corresponding to each vibration frequency; Indicates The number of vibration frequencies contained in each main target sequence segment; Represents the absolute value symbol.

[0013] Furthermore, the severity of each fault component is obtained according to the interference of each fault component on the grinding chamber, and then the fault detection result is obtained, including the specific method of: in, Indicates The severity of the fault component in each main target sequence segment; Indicates the number of locations where vibration sensors are installed on the grinding chamber; Indicates The first The fault component data corresponds to the first The vibration energy value at each position; Indicates The first The vibration energy value of each fault component data; Indicates The number of fault component data contained in each main target sequence segment; Indicates the absolute value symbol; Preset Threshold , when the severity of the fault component in all main target sequence segments is greater than the threshold , it is determined that the motor is faulty.

[0014] An embodiment of the present invention provides a grinding device for chemical raw materials, including a grinding device body, a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any one of the steps of the method for detecting grinding faults of a chemical raw material.

[0015] The beneficial effects of the technical solution of the present invention are as follows: the grinding fault detection method of chemical raw materials provided in the present embodiment aims at the defect that the traditional method relies on the experience of operators and needs to be inspected and shut down for repair only after an obvious fault occurs in the equipment. Considering the combination of several data of the motor and the grinding bin body during operation, according to the abnormality of the motor vibration data time series, the target sequence segment is screened out to understand the correlation between the motor vibration data and the bin body vibration data; then, based on several data of the motor and the grinding bin body during operation, the interference delay of the target sequence segment on each motor vibration data is obtained, and the probability that the motor vibration is interfered by the grinding bin body vibration is further calculated to obtain the main target sequence segment; the motor vibration data in the main target sequence segment is analyzed to obtain the fault component, which can help determine the specific location of the fault and facilitate targeted maintenance; at the same time, according to the interference of each fault component on the grinding bin body, the severity of each fault component is obtained, and then the fault detection result is obtained, and the fault source is accurately located. By using data analysis technology, a more objective and scientific basis for fault judgment can be obtained, and the deviation relying on manual experience can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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.

[0017] Figure 1 The present invention is a flow chart of the steps of a method for detecting grinding faults of chemical raw materials. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the grinding fault detection method of a chemical raw material proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of the grinding fault detection method for chemical raw materials provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1, which shows a flow chart of the steps of a grinding fault detection method for chemical raw materials provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Acquire some data of the motor and the grinding chamber during operation.

[0022] It should be noted that during the grinding process, the unevenness of the chemical raw materials will cause uneven force on the grinding bin, which will in turn affect the vibration stability of the grinding bin. The vibration stability of the grinding bin will interfere with the vibration data of the motor. Therefore, it is difficult to determine whether the abnormality in the motor vibration data is caused by a fault in the motor itself or by interference from the vibration of the grinding bin.

[0023] Specifically, in order to implement the grinding fault detection method for chemical raw materials proposed in this embodiment, it is first necessary to collect some data of the motor and the grinding chamber during operation. The specific process is as follows: Vibration sensors are installed at different positions of the grinding bin to obtain vibration data at different positions during the grinding process. The data are sorted in the order of collection time and recorded as the bin vibration data time series. An acceleration sensor is installed at the motor to obtain the vibration information of the motor through a vibration analyzer. The data are sorted in the order of collection time and recorded as the motor vibration data time series. The distance from different positions of the grinding bin to the motor is obtained.

[0024] So far, several data of the motor and the grinding chamber during operation are obtained through the above method.

[0025] Step S002: Filter out the target sequence segment according to the abnormality of the motor vibration data sequence; obtain the interference delay of the target sequence segment on each motor vibration data based on a number of data of the motor and the grinding chamber body during operation, further calculate the probability that the motor vibration is interfered by the grinding chamber body vibration, and obtain the main target sequence segment from the target sequence segment; analyze the motor vibration data in the main target sequence segment to obtain the fault component.

[0026] It should be noted that due to the unevenness of chemical raw materials themselves, such as uneven distribution of particle size and inconsistent density, the grinding bin will be subjected to uneven force during grinding. This uneven force will cause unstable vibration of the grinding bin, which will then be fed back to the motor and affect the stability of the motor vibration data. The vibration of the bin during the grinding process causes abnormal vibration data of the motor. The abnormality of the motor will be reflected in the vibration signals at different positions of the grinding bin. The probability of the instability of the motor vibration data being disturbed by the vibration of the bin is calculated.

[0027] Specifically, in step 2.1, the target sequence segment is screened out according to the abnormality degree of the motor vibration data time series.

[0028] It should be noted that the fast Fourier transform can convert time domain signals into frequency domain signals, so as to observe the amplitudes of different frequency components in the signal. The main frequency is the frequency component with the largest amplitude in the spectrum, which usually reflects the dominant vibration mode of the system. The stability of the main frequency reflects the stability of the main vibration mode of the system. If the main frequency changes frequently or is unstable, the vibration mode of the system will also become unstable.

[0029] The motor vibration data time series is divided into several sequence segments, and each sequence segment is subjected to fast Fourier transform to obtain the vibration energy values ​​and spectra corresponding to the several sequence segments. The frequency component with the largest amplitude in the spectrum of each sequence segment is obtained as the main frequency of the sequence segment, which is recorded as ; The frequency bandwidth range of the sequence segment is preset according to the main frequency of each sequence segment. According to the corresponding vibration energy value and frequency bandwidth range of the sequence segment, the abnormality degree of the sequence segment is calculated.

[0030] It should be noted that the frequency bandwidth range of each sequence segment is preset as follows according to experience in the embodiment of the present invention. , can be adjusted according to actual conditions, and this embodiment does not make any specific limitation.

[0031] As an embodiment, a specific method for calculating the abnormality degree of a sequence segment is: Among them, Indicates The degree of abnormality of each sequence segment; Indicates the number of all sequence segments in the motor vibration data time series; Indicates The number of data contained in each sequence segment; Indicates In the sequence segment The vibration energy value corresponding to each position; Indicates that except The first sequence segment outside In the sequence segment The vibration energy value corresponding to each position; Indicates the preset The sum of all vibration energy values ​​within the frequency bandwidth of a sequence segment; Represents the sum of all vibration energy values ​​within the frequency bandwidth of all sequence segments; Indicates the absolute value symbol; represents an exponential function with a natural constant as base; Represents the normalization function.

[0032] It should be noted that The larger the value, the The more prominent the main frequency of a sequence segment is, and the frequency components are mainly concentrated near the main frequency, the higher the frequency stability is, which means the abnormality of the sequence segment is smaller.

[0033] Preset Threshold , the sequence segments whose abnormality is greater than or equal to the preset threshold are recorded as target sequence segments.

[0034] It should be noted that the threshold for screening target sequence segments is preset based on experience in this embodiment. , can be adjusted according to actual conditions, and this embodiment does not make any specific limitation.

[0035] Step 2.2, based on several data of the motor and the grinding chamber during operation, obtain the interference delay of the target sequence segment on each motor vibration data, further calculate the probability that the motor vibration is interfered by the grinding chamber vibration, and obtain the main target sequence segment from the target sequence segment.

[0036] It should be noted that due to the interference caused by the vibration data of the grinding bin body, the motor vibration data will be abnormal, but this abnormality caused by interference will not occur immediately, and there will be a certain time delay. The more similar the grinding bin body vibration data is to the motor vibration data after a certain time delay, the lower the credibility of the abnormality of the motor vibration data in this sequence segment. That is, the abnormality of the motor vibration data at this time is caused by the interference caused by the normal vibration of the grinding bin body when grinding chemical raw materials. Therefore, the probability of the motor vibration data in different sequence segments being interfered by the grinding bin body vibration data is obtained based on the correlation between the vibration data at different positions of the grinding bin body and the motor vibration data.

[0037] The position of the grinding chamber closest to the motor is taken as the reference position, and the least square method is used to fit all the motor vibration data in each target sequence segment to obtain the slope of each motor vibration data on the fitting curve; the difference between the slope of the data in the target sequence segment on the fitting curve and the slope corresponding to the vibration data of the grinding chamber at the reference position is calculated, and the threshold is preset. , the vibration data of the grinding chamber corresponding to the difference value being less than the preset threshold value is recorded as the target data.

[0038] It should be noted that the threshold for screening target data is preset based on experience in this embodiment. , can be adjusted according to actual conditions, and this embodiment does not make any specific limitation.

[0039] Among all target data corresponding to the motor vibration data, the difference between the time corresponding to the previous target data closest to the motor vibration data and the acquisition time of the motor vibration data is used as the reference delay of the motor vibration data. The average of the reference delays of all motor vibration data in the target sequence segment is used as the interference delay of the vibration of the grinding chamber body on the motor vibration data.

[0040] As an embodiment, a specific method for calculating the interference delay of the target sequence segment on each motor vibration data is as follows: in, Indicates the vibration of the grinding chamber The interference delay of each motor vibration data in the target sequence segment is Indicates The number of motor vibration data in the target sequence segment, Indicates The target sequence segment The reference delay of the motor vibration data.

[0041] As an embodiment, a specific method for calculating the probability that the motor vibration of the target sequence segment is disturbed by the grinding chamber vibration is as follows: in, Indicates The probability that the motor vibration of a target sequence segment is disturbed by the vibration of the grinding chamber; Indicates The degree of abnormality of the target sequence segment; Indicates The number of motor vibration data in the target sequence segment; Indicates The first Motor vibration data; Indicates that for the reference position The first The motor vibration data is delayed during the interference The corresponding grinding chamber vibration data; Indicates Pearson correlation coefficient between the motor vibration data of the target sequence segment and the grinding chamber vibration data of the reference position; Indicates the vibration of the grinding chamber The interference delay of each motor vibration data in the target sequence segment; Indicates the absolute value symbol; Represents an exponential function with a natural constant as its base.

[0042] It should be noted that Indicates the similarity between two vibration data. The closer the ratio is to 1, the The greater the probability that the motor vibration data on a target sequence segment is interfered by the warehouse vibration data. Indicates The probability that the instability of the motor vibration in the target sequence segment is affected by the motor itself, the smaller the interference delay, the The larger the Pearson correlation coefficient between the motor vibration data of the target sequence segment and the grinding chamber vibration data of the reference position, the The greater the probability that the motor vibration data of the target sequence segment is affected by the motor itself, the corresponding The smaller the probability that the motor vibration of each target sequence segment is disturbed by the vibration of the grinding chamber is.

[0043] Preset Threshold , when the probability that the motor vibration data of the target sequence segment is disturbed by the warehouse vibration data is greater than the threshold When the probability that the motor vibration data of the target sequence segment is disturbed by the warehouse vibration data is less than or equal to the threshold , the target sequence segment is marked as the main target sequence segment.

[0044] It should be noted that when the probability that the motor vibration data of the target sequence segment is disturbed by the warehouse vibration data is greater than the threshold When the probability that the motor vibration data of the target sequence segment is disturbed by the warehouse vibration data is less than or equal to the threshold , it means that the motor vibration data is unstable at this time, which is caused by the motor itself.

[0045] It should be noted that the threshold for selecting the main target sequence segment is preset based on experience in this embodiment. , can be adjusted according to actual conditions, and this embodiment does not make any specific limitation.

[0046] Step 2.3, analyze the motor vibration data in the main target sequence segment to obtain the fault component.

[0047] It should be noted that when a motor fails, the faulty part will generate vibrations of a specific frequency, causing the vibration energy value of the vibration frequency to change significantly, which is different from the numerical distribution under normal conditions. Based on the difference between the vibration energy value of each vibration frequency and the vibration energy values ​​of other vibration frequencies, the possibility of each vibration frequency being a fault component is obtained.

[0048] According to the difference in vibration energy values ​​between each vibration frequency and other vibration frequencies, combined with the probability that the motor vibration is disturbed by the grinding chamber vibration, the possibility that the vibration frequency in the main target sequence segment is a fault component is calculated.

[0049] As an embodiment, a method for specifically calculating the possibility that the vibration frequency in the main target sequence segment is a fault component is as follows: in, Indicates The first The possibility that a vibration frequency is a fault component; Indicates The first The probability that the motor vibration data of the main target sequence segment where the vibration frequency is located is interfered by the grinding chamber vibration data; Indicates The first The vibration energy value corresponding to each vibration frequency; Indicates In the main target sequence segments, except The vibration frequency other than The vibration energy value corresponding to each vibration frequency; Indicates The number of vibration frequencies contained in each main target sequence segment; Represents the absolute value symbol.

[0050] It should be noted that when the motor itself fails, the abnormality of the vibration data will persist, that is, abnormality will also occur in the next time period. The first The greater the abnormality of the vibration frequency and the greater the correlation with the same vibration frequency in the next adjacent time period, the greater the abnormality of the vibration frequency. The first The smaller the difference, the smaller the possibility that the component is a fault component; the larger the difference, the greater the possibility that the vibration frequency is a fault component.

[0051] The first The vibration frequency with the greatest possibility of fault component in the main target sequence segment is recorded as the fault component.

[0052] So far, the fault component is obtained through the above method.

[0053] Step S003: According to the interference of each fault component on the grinding chamber, the severity of each fault component is obtained, and then the fault detection result is obtained.

[0054] As an embodiment, a specific method for calculating the severity of each fault component is as follows: in, Indicates The severity of the fault component in each main target sequence segment; Indicates the number of locations where vibration sensors are installed on the grinding chamber; Indicates The first The fault component data corresponds to the first The vibration energy value at each position; Indicates The first The vibration energy value of each fault component data; Indicates The number of fault component data contained in each main target sequence segment; Represents the absolute value symbol.

[0055] It should be noted that Indicates The vibration energy value of the fault component in the first main target sequence segment is The difference in the vibration energy values ​​of the grinding bin at different positions is smaller, indicating that the fault is more consistent with the vibration data of the bin, and the severity of the motor fault is greater.

[0056] Preset Threshold , when the severity of the fault components in all main target sequence segments is greater than the threshold , it is determined that the motor is faulty.

[0057] It should be noted that the threshold for selecting the main target sequence segment is preset based on experience in this embodiment. , can be adjusted according to actual conditions, and this embodiment does not make any specific limitation.

[0058] Through the above steps, a grinding fault detection method for chemical raw materials is completed.

[0059] On the other hand, an embodiment of the present invention provides a grinding device for chemical raw materials, including a grinding device body and a memory, a processor and a computer program stored in the memory and executable on the processor contained in the grinding device, wherein when the processor executes the computer program, steps S001 to S003 of a method for detecting grinding faults of chemical raw materials are implemented.

[0060] The present embodiment provides a method for detecting grinding faults of chemical raw materials. In view of the defects that the traditional method relies on the experience of operators and needs to be shut down for inspection and repair only after an obvious fault occurs in the equipment, the method takes into account a number of data of the motor and the grinding bin body during operation, and according to the abnormality of the motor vibration data time series, a target sequence segment is screened out to understand the correlation between the motor vibration data and the bin body vibration data; then, based on a number of data of the motor and the grinding bin body during operation, the interference delay of the target sequence segment on each motor vibration data is obtained, and the probability that the motor vibration is interfered by the grinding bin body vibration is further calculated to obtain the main target sequence segment; the motor vibration data in the main target sequence segment is analyzed to obtain the fault component, which can help determine the specific location of the fault and facilitate targeted maintenance; at the same time, according to the interference of each fault component on the grinding bin body, the severity of each fault component is obtained, and then the fault detection result is obtained, and the fault source is accurately located. By using data analysis technology, a more objective and scientific basis for fault judgment can be obtained, and the deviation relying on manual experience can be reduced.

[0061] It should be noted that the The model is only used to represent negative correlation and constrain the output of the model to be in In the specific implementation, it can be replaced by other models with the same purpose. The model is described as an example without any specific limitation. is the input to the model.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting grinding faults of chemical raw materials, characterized in that: The method comprises the following steps: Acquire several data of the motor and the grinding chamber during operation; the several data are vibration frequency data obtained by using a vibration sensor, and the distances from different positions of the grinding chamber to the motor; the vibration frequency data includes a chamber vibration data time series and a motor vibration data time series; According to the abnormal degree of the motor vibration data time series, a target sequence segment is screened out; the position of the grinding chamber body closest to the motor is taken as the reference position, and the average difference between the corresponding time of the adjacent target data closest to the motor vibration data and the acquisition time of the motor vibration data is obtained as the interference delay of the target sequence segment to each motor vibration data, the target data is the vibration data of the grinding chamber body when the difference in the change rate between the target sequence segment and the vibration data of the grinding chamber body at the reference position is less than a preset threshold, and the probability that the motor vibration is interfered by the vibration of the grinding chamber body is further calculated, and the probability is positively correlated with the interference delay of the grinding chamber body to each motor vibration data in the target sequence segment, and negatively correlated with the vibration data of the grinding chamber body at the time before the corresponding interference delay of the motor vibration data at the reference position causing interference to the motor vibration data in the target sequence segment, and the main target sequence segment is obtained from the target sequence segment; the motor vibration data in the main target sequence segment is analyzed to obtain the fault component; According to the interference of each fault component on the grinding chamber body, the severity of each fault component is obtained, and then the fault detection result is obtained.

2. A method for detecting grinding faults of chemical raw materials according to claim 1, characterized in that: The method of selecting the target sequence segment according to the abnormality of the motor vibration data time series includes: The motor vibration data time series is equally divided into several sequence segments, and each sequence segment is subjected to fast Fourier transform to obtain the vibration energy values ​​and spectra corresponding to the several sequence segments; the frequency component with the largest amplitude in the spectrum of each sequence segment is obtained as the main frequency of the sequence segment, which is recorded as ; Preset the frequency bandwidth range of the sequence segment according to the main frequency of each sequence segment; According to the vibration energy value and frequency bandwidth range corresponding to each sequence segment, the abnormality degree of the sequence segment is calculated; Preset Threshold , the sequence segments whose abnormality is greater than or equal to the preset threshold are recorded as target sequence segments.

3. A method for detecting grinding faults of chemical raw materials according to claim 2, characterized in that: The specific method of calculating the abnormality degree of the sequence segment according to the vibration energy value and frequency bandwidth range corresponding to each sequence segment is as follows: in, Indicates The degree of abnormality of each sequence segment; Indicates the number of all sequence segments in the motor vibration data time series; Indicates The number of data contained in each sequence segment; Indicates In the sequence segment The vibration energy value corresponding to each position; Indicates that except The first sequence segment outside In the sequence segment The vibration energy value corresponding to each position; Indicates the preset The sum of all vibration energy values ​​within the frequency bandwidth of a sequence segment; Represents the sum of all vibration energy values ​​within the frequency bandwidth of all sequence segments; Indicates the absolute value symbol; represents an exponential function with a natural constant as base; Represents the normalization function.

4. The method for detecting grinding faults of chemical raw materials according to claim 1, characterized in that: The specific method for obtaining the interference delay of the target sequence segment on each motor vibration data is as follows: Use the least squares method to fit all motor vibration data in each target sequence segment to obtain the slope of each motor vibration data on the fitting curve; calculate the difference between the slope of the data in the target sequence segment on the fitting curve and the slope corresponding to the vibration data of the grinding chamber at the reference position, and preset the threshold , recording the vibration data of the grinding chamber corresponding to the difference being less than a preset threshold as target data; Among all the target data corresponding to the motor vibration data, the difference between the time corresponding to the previous target data closest to the motor vibration data and the acquisition time of the motor vibration data is used as the reference delay of the motor vibration data. The average of the reference delays of all motor vibration data in the target sequence segment is used as the interference delay of the vibration of the grinding chamber body on the motor vibration data.

5. The method for detecting grinding faults of chemical raw materials according to claim 1, characterized in that: The specific method for calculating the probability that the motor vibration is disturbed by the grinding chamber vibration is as follows: in, Indicates The probability that the motor vibration of a target sequence segment is disturbed by the vibration of the grinding chamber; Indicates The degree of abnormality of the target sequence segment; Indicates The number of motor vibration data in the target sequence segment; Indicates The target sequence segment Motor vibration data; Indicates that for the reference position The first The motor vibration data is delayed during the interference The corresponding grinding chamber vibration data; Indicates Pearson correlation coefficient between the motor vibration data of the target sequence segment and the grinding chamber vibration data of the reference position; Indicates the vibration of the grinding chamber The interference delay of each motor vibration data in the target sequence segment; Indicates the absolute value symbol; Represents an exponential function with a natural constant as its base.

6. The method for detecting grinding faults of chemical raw materials according to claim 1, characterized in that: The method of obtaining the main target sequence segment from the target sequence segment includes: presetting a threshold , when the probability that the motor vibration data of the target sequence segment is disturbed by the warehouse vibration data is greater than the threshold When the probability that the motor vibration data of the target sequence segment is disturbed by the warehouse vibration data is less than or equal to the threshold When , the target sequence segment is marked as the main target sequence segment.

7. A method for detecting grinding faults of chemical raw materials according to claim 1, characterized in that: The specific method of analyzing the motor vibration data in the main target sequence segment to obtain the fault component includes: According to the difference in vibration energy values ​​between each vibration frequency and other vibration frequencies, combined with the probability that the motor vibration is disturbed by the grinding chamber vibration, the possibility that the vibration frequency in the main target sequence segment is a fault component is calculated; The first The vibration frequency with the greatest possibility of fault component in the main target sequence segment is recorded as the fault component.

8. A method for detecting grinding faults of chemical raw materials according to claim 7, characterized in that: The specific method of calculating the possibility that the vibration frequency in the main target sequence segment is a fault component includes: in, Indicates The first The possibility that a vibration frequency is a fault component; Indicates The first The probability that the motor vibration data of the main target sequence segment where the vibration frequency is located is interfered by the grinding chamber vibration data; Indicates The first The vibration energy value corresponding to each vibration frequency; Indicates In the main target sequence segments, except The vibration frequency other than The vibration energy value corresponding to each vibration frequency; Indicates The number of vibration frequencies contained in each main target sequence segment; Represents the absolute value symbol.

9. The method for detecting grinding faults of chemical raw materials according to claim 1, characterized in that: The method of obtaining the severity of each fault component according to the interference of each fault component on the grinding chamber body and then obtaining the fault detection result includes the following specific methods: in, Indicates The severity of the fault component in each main target sequence segment; Indicates the number of locations where vibration sensors are installed on the grinding chamber; Indicates The first The fault component data corresponds to the first The vibration energy value at each position; Indicates The first The vibration energy value of each fault component data; Indicates The number of fault component data contained in each main target sequence segment; Indicates the absolute value symbol; Preset Threshold , when the severity of the fault component in all main target sequence segments is greater than the threshold , it is determined that the motor is faulty.

10. A grinding device for chemical raw materials, comprising a grinding device body, a memory contained in the grinding device, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images