Environment-friendly building block production control method and device

Abstract

The invention relates to the technical field of building material production control, in particular to an environment-friendly building block production control method and device. According to the method, suspected abnormal motor vibration data segments are screened out in the current production cycle based on the difference of motor vibration data in different production cycles. And determining vibration trend components of the suspected abnormal motor vibration data by comparing a comparison data segment formed by the suspected abnormal motor vibration data segment and the corresponding bin body vibration data. And the vibration consistency can be obtained by comparing the vibration trend component with the principal component in the comparison data segment. And further combining information in the suspected abnormal motor vibration data segment to determine the abnormal degree of the abnormal moment so as to control the motor. According to the method, the motor vibration data and the bin body vibration data are compared through component decomposition and component screening, then the accurate abnormal degree is determined for motor control, misjudgment of abnormal data caused by noise on control can be avoided through quantification of the abnormal degree, and the control precision is improved.

Description

Technical Field

[0001] The invention relates to the technical field of building material production control, and in particular to an environmentally friendly building block production control method and device. Background Art

[0002] Environmentally friendly building blocks are a kind of building material with environmentally friendly characteristics. They are widely used in the construction field. The existing production process of environmentally friendly building blocks is raw materials, mixing, molding, curing, and stacking. Among them, mixing is an important link in production, and the mixer is an important equipment in the mixing link. Its operating status affects the efficiency of the entire production line. Therefore, it is necessary to analyze the vibration data of the mixer motor and identify abnormalities in time to ensure the production efficiency of environmentally friendly building blocks.

[0003] The existing technology can determine whether the mixer is faulty by installing a vibration sensor at the mixing motor and judging by the vibration data during operation. Since the equipment system of the building block production line is complex and there are many types of equipment, it is easy to cause electromagnetic interference to the vibration sensor. Strong electromagnetic interference may introduce noise in the process of sensor signal transmission, making the collected vibration data contain noise. When performing fuzzy control, it is difficult to distinguish between the real vibration data and the data affected by electromagnetic interference, which reduces the accuracy of the control of the building block production process. Summary of the invention

[0004] In order to solve the technical problem that the real abnormal motor vibration data and the abnormal noise interference data cannot be distinguished in the prior art during the mixing process of building blocks, the purpose of the present invention is to provide an environmentally friendly building block production control method and device, and the technical scheme adopted is as follows: The present invention proposes an environmentally friendly building block production control method, the method comprising: Obtaining vibration data of the block production line to be controlled in each production cycle; the vibration data includes motor vibration data and silo vibration data at different positions of the mixing silo, and each production cycle includes multiple vibration data segments; According to the data difference between the motor vibration data segments between the current production cycle and the historical production cycle, the suspected abnormal motor vibration data segments in the current production cycle are obtained; The warehouse body vibration data segment in the time range corresponding to the suspected abnormal motor vibration data segment is used as the comparison data segment; the similarity of the principal components between the suspected abnormal motor vibration data segment and the comparison data segment is compared to screen out the vibration trend component of the suspected abnormal motor vibration data; the consistency between the vibration trend component and the principal component of the comparison data segment is analyzed to obtain the vibration consistency of the suspected abnormal motor vibration data segment; According to the data distribution of the suspected abnormal motor vibration data segment and the vibration consistency, the abnormality degree at the abnormal moment in the suspected abnormal motor vibration data segment is obtained; and the motor speed is controlled according to the abnormality degree at the abnormal moment.

[0005] Furthermore, the method for screening the suspected abnormal motor vibration data segment includes: Taking any motor vibration data segment in the current production cycle as the target data segment; obtaining the matching degree of the historical production cycle according to the difference between the target data segment and the motor vibration data segment at the same time sequence position in the historical production cycle, and screening out the matching cycle according to the matching degree; The suspected abnormal coefficient of the target data segment is obtained according to the matching degree and the number of the matching cycles, and whether the target data segment is a suspected abnormal motor vibration data segment is determined according to the suspected abnormal coefficient.

[0006] Furthermore, the method for obtaining the matching degree includes: The absolute value of the difference in average amplitude between the target data segment and the motor vibration data segment at the same time position in the historical production cycle is taken as the amplitude difference; the number of production cycles between the current production cycle and the historical production cycle is taken as the time difference; the product of the amplitude difference and the time difference is negatively correlated and normalized to obtain the matching degree.

[0007] Furthermore, the method for obtaining the suspected abnormality coefficient includes: The proportion of the matching cycle in all production cycles is obtained, the average matching degree of all matching cycles is obtained, the product of the proportion and the average matching degree is negatively correlated and normalized to obtain the suspected abnormality coefficient.

[0008] Furthermore, the method for screening the vibration trend component includes: Any principal component of the suspected abnormal motor vibration data segment is used as the target principal component; the principal component of the comparison data segment is used as the comparison principal component, the characteristic value and value of the comparison principal component and the target principal component are obtained, and the difference distance between the comparison principal component and the target principal component is obtained; the ratio of the characteristic value and value to the difference distance is used as the initial similarity factor, and the comparison principal component with the largest initial similarity factor is selected in each comparison data segment as the similar principal component of the target principal component; the cumulative value of the initial similarity factors corresponding to the similar principal components of all comparison data segments is used as the component screening factor of the target principal component; Among the principal components of the suspected abnormal motor vibration data segment, the principal component with the largest component screening factor is selected as the vibration trend component.

[0009] Furthermore, the method for obtaining the vibration consistency includes: A negative correlation mapping is performed between the position distance between the corresponding position of the comparison data segment and the motor to obtain the position confidence of each comparison data segment; the product of the initial similarity factor between the vibration trend component and the similar principal component in the comparison data segment and the position confidence is used as the initial consistency of the comparison data segment; after accumulating the initial consistency of all comparison data segments, it is multiplied by the component screening factor corresponding to the vibration trend component to obtain the vibration consistency.

[0010] Furthermore, the method for screening abnormal moments includes: The suspected abnormal motor vibration data segment whose vibration consistency is greater than a preset consistency threshold is taken as an abnormal data segment, and each moment in the abnormal data segment is taken as an abnormal moment.

[0011] Furthermore, the method for obtaining the abnormality degree includes: In the abnormal data segment, the difference between the motor vibration data at the abnormal moment and the next moment is normalized to obtain the vibration instability at the abnormal moment; the product of the vibration instability and the vibration consistency is normalized to obtain the abnormal degree at the abnormal moment.

[0012] Further, controlling the motor speed according to the abnormality degree at each moment includes: If a preset number of moments are abnormal moments in succession and the degree of abnormality is greater than a preset abnormality threshold, the motor is controlled to reduce the speed.

[0013] The present invention also proposes an environmentally friendly building block production control device, the device comprising: A vibration data acquisition module is used to acquire vibration data of the block production line to be controlled in each production cycle; the vibration data includes motor vibration data and silo vibration data at different positions of the mixing silo, and each production cycle includes multiple vibration data segments; A suspected abnormal screening module is used to obtain suspected abnormal motor vibration data segments in the current production cycle based on the data difference between the motor vibration data segments between the current production cycle and the historical production cycle; A vibration trend component screening module is used to use the warehouse body vibration data segment within the time range corresponding to the suspected abnormal motor vibration data segment as a comparison data segment; compare the similarity of the principal components between the suspected abnormal motor vibration data segment and the comparison data segment, and screen out the vibration trend component of the suspected abnormal motor vibration data; A vibration consistency analysis module, used to analyze the consistency between the vibration trend component and the main component of the comparison data segment, and obtain the vibration consistency of the suspected abnormal motor vibration data segment; The motor speed control module is used to obtain the abnormality degree at each moment in the suspected abnormal motor vibration data segment according to the data distribution of the suspected abnormal motor vibration data segment and the vibration consistency; and control the motor speed according to the abnormality degree at each moment.

[0014] The present invention has the following beneficial effects: The present invention screens out suspected abnormal motor vibration data segments in the current production cycle based on the difference in motor vibration data in different production cycles. Considering that the abnormal vibration of the motor will be transmitted to other positions of the mixing bin due to the structure of the mixing bin, that is, the abnormal vibration should have a certain consistency with the vibration data of the mixing bin body, and the noise is noise data generated by electromagnetic interference, so the abnormal data expressed is not consistent with the vibration data of the bin body. Therefore, the present invention determines the vibration trend component of the suspected abnormal motor vibration data by comparing the suspected abnormal motor vibration data segment with the corresponding bin body vibration data. The vibration trend component can effectively characterize the vibration information in the suspected abnormal motor vibration data segment, and the interference of other components on the vibration consistency analysis can be avoided by component decomposition, and then the vibration consistency can be obtained by comparing the vibration trend component with the main component in the comparison data segment. Further, the abnormal degree at the abnormal moment is determined in combination with the information in the suspected abnormal motor vibration data segment for controlling the motor. The present invention compares the motor vibration data and the bin body data through component decomposition and component screening, and then determines the accurate abnormal degree for motor control. The quantification of the abnormal degree can avoid the misjudgment of the abnormal data on the control caused by noise, and improve the control accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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.

[0016] Figure 1 The present invention provides a flow chart of an environmentally friendly building block production control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] 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 an environmentally friendly building block production control method and device proposed by the present invention, its specific implementation method, structure, features and effects, in conjunction 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.

[0018] 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.

[0019] The specific scheme of an environmentally friendly building block production control method and device provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of an environmentally friendly building block production control method provided by an embodiment of the present invention, the method comprising: Step S1: Obtain vibration data of the block production line to be controlled in each production cycle; the vibration data includes motor vibration data and silo vibration data at different positions of the mixing silo, and each production cycle includes multiple vibration data segments.

[0021] In the production process of building blocks, different production cycles are set according to the production batches. In the embodiment of the present invention, the time for producing 50 blocks is used as a production cycle. A vibration sensor is installed on the motor of the mixing bin, and vibration sensors are evenly installed at different positions on the bin body of the mixing bin to collect vibration data. In the embodiment of the present invention, the collection frequency of the vibration sensor is once every 5 seconds, and the vibration data collected in one production cycle is divided into 30 data segments, thereby obtaining the bin body vibration data segment and the motor vibration data segment.

[0022] Step S2: obtaining suspected abnormal motor vibration data segments in the current production cycle according to the data difference between the motor vibration data segments in the current production cycle and the historical production cycles.

[0023] In the production process of building blocks, for the same production line, the wear process experienced by the mixer equipment in continuous production cycles is gradual and relatively uniform, and the raw materials put into the mixer each time are basically similar in type, particle size, humidity, ratio, etc., and each production cycle is usually under the same working condition. The similarity of the raw material characteristics makes the load borne by the mixer motor during the mixing process similar, which will produce similar vibration data. Therefore, for the current production cycle, the suspected abnormal motor vibration data segment in the current production cycle can be screened out by comparing the data differences between the motor vibration data segments of the historical production cycle and the current production cycle. Among them, the suspected abnormal motor vibration data segment contains obviously abnormal data features, which may be caused by abnormal vibration or noise, causing the need for further analysis in subsequent steps.

[0024] Preferably, in the embodiment of the present invention, for the current production cycle, the production cycles before it are all historical production cycles, so there are more historical production cycles. In order to increase the accuracy of vibration data comparison, the embodiment of the present invention first screens out the matching cycle of the current production cycle, and then determines the suspected abnormal motor vibration data segment by comparing the motor vibration data between the current production cycle and the matching cycle. The specific method for screening the suspected abnormal motor vibration data segment includes: Any motor vibration data segment in the current production cycle is used as the target data segment; the matching degree of the historical production cycle is obtained based on the difference between the target data segment and the motor vibration data segment at the same time sequence position in the historical production cycle, and the matching cycle is screened out based on the matching degree. That is, the greater the matching degree, the more similar the motor vibration data segments between the two production cycles are, and the more matching cycles, the more similar the target data segment in the current production cycle has vibration characteristics, and the less likely the target data segment is abnormal vibration.

[0025] Further, the suspected abnormality coefficient of the target data segment is obtained according to the matching degree and number of matching cycles, and whether the target data segment is a suspected abnormal motor vibration data segment is determined according to the suspected abnormality coefficient. That is, the suspected abnormality coefficient should be negatively correlated with the matching degree and the number of matching cycles. The greater the matching degree and the more matching cycles, the smaller the suspected abnormality coefficient.

[0026] In the embodiment of the present invention, after the suspected abnormal coefficient is normalized, the abnormal coefficient threshold is set to 0.7, and the target data segment with the suspected abnormal coefficient greater than the abnormal coefficient threshold is used as the suspected abnormal motor vibration data segment.

[0027] Furthermore, in an embodiment of the present invention, the method for obtaining the matching degree includes: The absolute value of the difference in average amplitude between the target data segment and the motor vibration data segment at the same time sequence position in the historical production cycle is taken as the amplitude difference. The greater the amplitude difference, the greater the difference in vibration data between the two motor vibration data segments, and the less the historical production cycle matches the current production cycle.

[0028] The number of production cycles between the current production cycle and the historical production cycle is taken as the time difference. That is, the larger the time difference, the greater the time distance between the two production cycles, the greater the loss in the mixing process, and the more dissimilar the characteristics produced, the lower the matching degree should be.

[0029] Therefore, the product of the amplitude difference and the time difference is negatively correlated and normalized to obtain a matching degree. In an embodiment of the present invention, the method of negative correlation mapping and normalization is: the opposite number of the data is used as the power of an exponential function with a natural constant as the base, and the function output result is the result of negative correlation mapping and normalization of the corresponding data. Those skilled in the art may choose other basic mathematical means to achieve negative correlation mapping and normalization, which will not be limited or elaborated here, and will not be repeated in subsequent content.

[0030] In the embodiment of the present invention, the matching degree threshold is set to 0.7, and the historical production cycle with a matching degree greater than the matching degree threshold is used as the matching cycle of the current production cycle.

[0031] Furthermore, the method for obtaining the suspected abnormality coefficient includes: The proportion of matching cycles in all production cycles is obtained, the average matching degree of all matching cycles is obtained, the product of the quantity proportion and the average matching degree is negatively correlated and normalized to obtain the suspected abnormality coefficient.

[0032] Step S3: Use the warehouse vibration data segment within the corresponding time range of the suspected abnormal motor vibration data segment as the comparison data segment; compare the similarity of the principal components between the suspected abnormal motor vibration data segment and the comparison data segment, and screen out the vibration trend component of the suspected abnormal motor vibration data; analyze the consistency between the vibration trend component and the principal component of the comparison data segment, and obtain the vibration consistency of the suspected abnormal motor vibration data segment.

[0033] The motor of the mixer is the core driving component of the overall system, and the abnormal vibration it generates will have a direct impact on the entire mixer. The mixer motor is the power source for the operation of the mixer bin. The motor and the mixer bin are connected by various connecting parts. The power generated when the motor is running will be directly transmitted to the stirring device, driving the materials inside the bin to stir. Therefore, under normal circumstances, the vibration of the motor and the bin has a high consistency due to factors such as power transmission and structural association. Therefore, the bin vibration data at different positions of the mixer bin will produce consistent vibration characteristics with the abnormal vibration of the motor, while the abnormal motor vibration data caused by noise will not have a significant correlation with the bin vibration data. Therefore, in order to analyze the consistency between the two types of data, it is first necessary to screen out the suspected abnormal motor vibration data segment for the characteristic data of vibration trend analysis.

[0034] Because the purpose of screening out the vibration trend is to compare the warehouse vibration and the motor vibration, the embodiment of the present invention compares the similarity of the principal components between the suspected abnormal motor vibration data segment and the comparison data segment, and screens out the vibration trend component of the suspected abnormal motor vibration data. That is, the more similar the principal component is, the more it can be used to analyze the consistency of the vibration trend, and the greater the reference significance of its vibration trend. Therefore, the vibration trend component in the suspected abnormal motor vibration data can be screened out based on the similarity. Then, the vibration consistency is determined by using the consistency of the vibration trend component and the principal component in the comparison data segment. The greater the vibration consistency, the more the abnormal vibration in the suspected abnormal motor vibration data is a real abnormal vibration.

[0035] In the embodiment of the present invention, the principal components of all data segments are obtained through the PCA principal component analysis algorithm, and each principal component obtained has a corresponding eigenvalue. The larger the eigenvalue, the more important the information of the principal component in the current data segment.

[0036] Preferably, in an embodiment of the present invention, the method for screening vibration trend components includes: Any principal component of the suspected abnormal motor vibration data segment is used as the target principal component; the principal component of the comparison data segment is used as the comparison principal component.

[0037] Obtain the eigenvalues ​​and values ​​of the comparison principal component and the target principal component. The larger the eigenvalues ​​and values, the more important the two principal components are in the corresponding data segment, and the more suitable they are for trend analysis.

[0038] The difference distance between the comparison principal component and the target principal component is obtained. The smaller the difference distance, the more similar the two principal components are, and the corresponding target principal component is more likely to be the vibration trend component used to characterize the vibration trend.

[0039] The ratio of the eigenvalue and the difference distance is used as the initial similarity factor. The larger the initial similarity factor, the more similar the comparison principal component is to the target principal component. In each comparison data segment, the comparison principal component with the largest initial similarity factor is selected as the similar principal component of the target principal component.

[0040] The cumulative value of the initial similarity factor corresponding to the similar principal components of all the comparison data segments is used as the component screening factor of the target principal component. The larger the component screening factor, the more similar the trend of the target principal component is to the vibration data of the warehouse at all positions, and the more the target principal component can represent the vibration trend information of the motor.

[0041] Therefore, among the principal components of the suspected abnormal motor vibration data segment, the principal component with the largest component screening factor is selected as the vibration trend component.

[0042] Furthermore, in an embodiment of the present invention, a method for obtaining vibration consistency includes: The position distance between the corresponding position of the comparison data segment and the motor is negatively correlated to obtain the position confidence of each comparison data segment. That is, the closer the sensor that collects the vibration data of the warehouse is to the motor, the more consistent the vibration characteristics are, and therefore the greater the position confidence.

[0043] The product of the initial similarity factor and the position confidence between the vibration trend component and the similar principal component in the comparison data segment is taken as the initial consistency of the comparison data segment. The greater the initial consistency, the more consistent the vibration trend component is with the vibration trend in the comparison data segment.

[0044] Further statistics are collected for all comparison data segments, and the initial consistency of all comparison data segments is accumulated, and then multiplied by the component screening factor corresponding to the vibration trend component to obtain the vibration consistency. That is, the corresponding component screening factor can be used as a reference weight. The larger the component screening factor, the more the vibration trend component can represent the vibration trend of the motor. The result obtained by multiplying it with the accumulated value of the initial consistency can be regarded as the result after weighted adjustment.

[0045] Step S4: according to the data distribution of the suspected abnormal motor vibration data segment and the vibration consistency, the abnormality degree at the abnormal moment in the suspected abnormal motor vibration data segment is obtained; and the motor speed is controlled according to the abnormality degree at the abnormal moment.

[0046] For the suspected abnormal motor vibration data segment, the more obvious the abnormal fluctuation represented by the data and the greater the vibration consistency, the greater the degree of abnormal motor vibration. Therefore, the degree of abnormality at the abnormal moment in the suspected abnormal motor vibration data segment can be obtained based on the data distribution of the suspected abnormal motor vibration data segment and the vibration consistency. Then the motor speed is controlled according to the degree of abnormality at the abnormal moment.

[0047] Preferably, in the embodiment of the present invention, since the vibration consistency can represent the abnormal situation of the suspected abnormal motor vibration data segment, the suspected abnormal motor vibration data segment can be screened based on the vibration consistency, and the suspected abnormal motor vibration data segment with a vibration consistency greater than a preset consistency threshold is taken as an abnormal data segment, and each moment in the abnormal data segment is taken as an abnormal moment. That is, the abnormal data segment is caused by abnormal vibration of the motor, and the suspected abnormal motor vibration data segment with a vibration consistency not greater than the preset consistency threshold is an abnormality caused by noise. In the embodiment of the present invention, the consistency threshold is set to 0.7.

[0048] Preferably, in an embodiment of the present invention, the method for obtaining the abnormality degree includes: In the abnormal data segment, the difference between the motor vibration data at the abnormal moment and the next moment is normalized to obtain the vibration instability at the abnormal moment; the product of vibration instability and vibration consistency is normalized to obtain the abnormal degree at the abnormal moment. That is, for an abnormal moment, if it produces obvious abnormal fluctuations and the vibration consistency of the corresponding data segment is large, it means that its abnormal degree is greater.

[0049] Preferably, in an embodiment of the present invention, for the current motor vibration data segment in the current production cycle, if it is an abnormal data segment, and a preset number of moments are abnormal moments in a row, and the degree of abnormality is greater than a preset abnormal threshold, the motor is controlled to reduce the speed. In an embodiment of the present invention, the preset number is set to 10, and the abnormal threshold is set to 0.6.

[0050] In other embodiments of the present invention, a positive integer 1 can be used as the weight of the motor vibration data at each moment in all normal time periods of the current production cycle, and the result obtained by adding 1 to the degree of abnormality is used as the weight of the motor vibration data at the kth abnormal moment of the current production cycle, thereby obtaining the weight of the motor vibration data at each moment in the current production cycle. Then, the weighted motor vibration data time series of the current production cycle is input into the fuzzy control system, and the control instruction for the motor speed is output. The fuzzy control system can dynamically adjust the production control strategy. When the system detects that there is high interference or abnormal vibration data in certain time periods, the system can adjust the weight so that data with less interference and high reliability have a greater impact on the decision. Therefore, the fuzzy control system can respond to the status of the production line in real time and make more precise adjustments to ensure the quality and efficiency of building block production.

[0051] In summary, the embodiment of the present invention screens out suspected abnormal motor vibration data segments in the current production cycle based on the differences in motor vibration data in different production cycles. By comparing the suspected abnormal motor vibration data segments with the corresponding comparison data segments composed of warehouse body vibration data, the vibration trend components of the suspected abnormal motor vibration data are determined. Then, the vibration consistency can be obtained by comparing the vibration trend components with the main components in the comparison data segments. The degree of abnormality at the abnormal moment is further determined in combination with the information in the suspected abnormal motor vibration data segments for controlling the motor. The present invention compares the motor vibration data and the warehouse body vibration data through component decomposition and component screening, and then determines the accurate degree of abnormality for motor control. The quantification of the degree of abnormality can avoid misjudgment of control by abnormal data caused by noise, thereby improving control accuracy.

[0052] Based on the same inventive concept, the present invention also proposes an environmentally friendly building block production control device, the device comprising: A vibration data acquisition module is used to acquire vibration data of the block production line to be controlled in each production cycle; the vibration data includes motor vibration data and silo vibration data at different positions of the mixing silo, and each production cycle includes multiple vibration data segments; A suspected abnormal screening module is used to obtain suspected abnormal motor vibration data segments in the current production cycle based on the data difference between the motor vibration data segments between the current production cycle and the historical production cycle; A vibration trend component screening module is used to use the warehouse body vibration data segment within the time range corresponding to the suspected abnormal motor vibration data segment as a comparison data segment; compare the similarity of the principal components between the suspected abnormal motor vibration data segment and the comparison data segment, and screen out the vibration trend component of the suspected abnormal motor vibration data; A vibration consistency analysis module, used to analyze the consistency between the vibration trend component and the main component of the comparison data segment, and obtain the vibration consistency of the suspected abnormal motor vibration data segment; The motor speed control module is used to obtain the abnormality degree at each moment in the suspected abnormal motor vibration data segment according to the data distribution of the suspected abnormal motor vibration data segment and the vibration consistency; and control the motor speed according to the abnormality degree at each moment.

[0053] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0054] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for controlling the production of environmentally friendly building blocks, characterized in that: The method comprises: Obtaining vibration data of the block production line to be controlled in each production cycle; the vibration data includes motor vibration data and silo vibration data at different positions of the mixing silo, and each production cycle includes multiple vibration data segments; According to the data difference between the motor vibration data segments between the current production cycle and the historical production cycle, the suspected abnormal motor vibration data segments in the current production cycle are obtained; The warehouse body vibration data segment in the time range corresponding to the suspected abnormal motor vibration data segment is used as the comparison data segment; the similarity of the principal components between the suspected abnormal motor vibration data segment and the comparison data segment is compared to screen out the vibration trend component of the suspected abnormal motor vibration data; the consistency between the vibration trend component and the principal component of the comparison data segment is analyzed to obtain the vibration consistency of the suspected abnormal motor vibration data segment; According to the data distribution of the suspected abnormal motor vibration data segment and the vibration consistency, the abnormality degree at the abnormal moment in the suspected abnormal motor vibration data segment is obtained; and the motor speed is controlled according to the abnormality degree at the abnormal moment.

2. The environmentally friendly building block production control method according to claim 1, characterized in that: The method for screening the suspected abnormal motor vibration data segment comprises: Taking any motor vibration data segment in the current production cycle as the target data segment; obtaining the matching degree of the historical production cycle according to the difference between the target data segment and the motor vibration data segment at the same time sequence position in the historical production cycle, and screening out the matching cycle according to the matching degree; The suspected abnormal coefficient of the target data segment is obtained according to the matching degree and the number of the matching cycles, and whether the target data segment is a suspected abnormal motor vibration data segment is determined according to the suspected abnormal coefficient.

3. The environmentally friendly building block production control method according to claim 2 is characterized in that: The method for obtaining the matching degree includes: The absolute value of the difference in average amplitude between the target data segment and the motor vibration data segment at the same time position in the historical production cycle is taken as the amplitude difference; the number of production cycles between the current production cycle and the historical production cycle is taken as the time difference; the product of the amplitude difference and the time difference is negatively correlated and normalized to obtain the matching degree.

4. The environmentally friendly building block production control method according to claim 2 is characterized in that: The method for obtaining the suspected abnormality coefficient includes: The proportion of the matching cycle in all production cycles is obtained, the average matching degree of all matching cycles is obtained, the product of the proportion and the average matching degree is negatively correlated and normalized to obtain the suspected abnormality coefficient.

5. The environmentally friendly building block production control method according to claim 1, characterized in that: The screening method of the vibration trend component includes: Any principal component of the suspected abnormal motor vibration data segment is used as the target principal component; the principal component of the comparison data segment is used as the comparison principal component, the characteristic value and value of the comparison principal component and the target principal component are obtained, and the difference distance between the comparison principal component and the target principal component is obtained; the ratio of the characteristic value and value to the difference distance is used as the initial similarity factor, and the comparison principal component with the largest initial similarity factor is selected in each comparison data segment as the similar principal component of the target principal component; the cumulative value of the initial similarity factors corresponding to the similar principal components of all comparison data segments is used as the component screening factor of the target principal component; Among the principal components of the suspected abnormal motor vibration data segment, the principal component with the largest component screening factor is selected as the vibration trend component.

6. The environmentally friendly building block production control method according to claim 5, characterized in that: The method for obtaining the vibration consistency includes: A negative correlation mapping is performed between the position distance between the corresponding position of the comparison data segment and the motor to obtain the position confidence of each comparison data segment; the product of the initial similarity factor between the vibration trend component and the similar principal component in the comparison data segment and the position confidence is used as the initial consistency of the comparison data segment; after accumulating the initial consistency of all comparison data segments, it is multiplied by the component screening factor corresponding to the vibration trend component to obtain the vibration consistency.

7. The environmentally friendly building block production control method according to claim 1, characterized in that: The method for screening abnormal moments includes: The suspected abnormal motor vibration data segment whose vibration consistency is greater than a preset consistency threshold is taken as an abnormal data segment, and each moment in the abnormal data segment is taken as an abnormal moment.

8. The environmentally friendly building block production control method according to claim 1, characterized in that: The method for obtaining the abnormality degree includes: In the abnormal data segment, the difference between the motor vibration data at the abnormal moment and the next moment is normalized to obtain the vibration instability at the abnormal moment; the product of the vibration instability and the vibration consistency is normalized to obtain the abnormal degree at the abnormal moment.

9. The environmentally friendly building block production control method according to claim 1, characterized in that: The controlling of the motor speed according to the abnormality degree at each moment comprises: If a preset number of moments are abnormal moments in succession and the degree of abnormality is greater than a preset abnormality threshold, the motor is controlled to reduce the speed.

10. An environmentally friendly building block production control device, characterized in that: The device comprises: A vibration data acquisition module is used to acquire vibration data of the block production line to be controlled in each production cycle; the vibration data includes motor vibration data and silo vibration data at different positions of the mixing silo, and each production cycle includes multiple vibration data segments; A suspected abnormal screening module is used to obtain suspected abnormal motor vibration data segments in the current production cycle based on the data difference between the motor vibration data segments between the current production cycle and the historical production cycle; A vibration trend component screening module is used to use the warehouse body vibration data segment within the time range corresponding to the suspected abnormal motor vibration data segment as a comparison data segment; compare the similarity of the principal components between the suspected abnormal motor vibration data segment and the comparison data segment, and screen out the vibration trend component of the suspected abnormal motor vibration data; A vibration consistency analysis module, used to analyze the consistency between the vibration trend component and the main component of the comparison data segment, and obtain the vibration consistency of the suspected abnormal motor vibration data segment; The motor speed control module is used to obtain the abnormality degree at each moment in the suspected abnormal motor vibration data segment according to the data distribution of the suspected abnormal motor vibration data segment and the vibration consistency; and control the motor speed according to the abnormality degree at each moment.

Images