CN118152733B - Rolling mill running state data processing method, device, computer equipment and medium - Google Patents

Abstract

The invention relates to the technical field of rolling mill equipment monitoring, and discloses a rolling mill running state data processing method, a device, computer equipment and a medium, wherein the method comprises the following steps: acquiring first vibration data of a vibration monitoring point on a monitored rolling mill; judging whether the first vibration data belongs to vibration data in a shutdown state or not; if the first vibration data does not belong to the vibration data in the shutdown state, judging whether the first vibration data belongs to interference data or not; if the first vibration data does not belong to the interference data, judging whether a first effective value of the first vibration data is larger than a first threshold value; and if the first effective value of the first vibration data is larger than the first threshold value, determining that the first vibration data is the vibration data in the startup loaded state. According to the technical scheme, effective data can be screened out from the collected vibration data, interference data is filtered out, and the purposes of reducing false alarm rate and improving diagnosis accuracy are achieved.

Description

Rolling mill operation status data processing method, device, computer equipment and medium

Technical Field

The present invention relates to the technical field of rolling mill equipment monitoring, and in particular to a rolling mill operating status data processing method, device, computer equipment and medium.

Background Art

In the field of rolling mill monitoring technology, vibration monitoring is a major means of monitoring the operating status of rolling mill equipment. By monitoring the mechanical vibration of different parts of the rolling mill equipment and analyzing and processing the vibration data obtained from the monitoring, fault diagnosis and fault warning of the rolling mill equipment can be achieved.

In actual industrial production, the automatic monitoring process of rolling mill equipment generally pays more attention to the situation when the machine is started with load. However, due to many interference factors generated by the on-site environment, the collected vibration data are not all for the situation when the machine is started with load. There are certain interference data, for example, the industrial equipment is operated without load for a long time. For example, during the continuous rolling of multiple steel bars, the front steel bar rolls out of the rolling mill, and the rear steel bar has not yet entered the rolling mill for a short period of time, resulting in low equipment fault diagnosis rate and low fault warning rate.

Therefore, there is an urgent need for a rolling mill operation status data processing method that can screen out valid data from the collected vibration data and filter out interference data, so as to reduce the false alarm rate and improve the diagnostic accuracy.

Summary of the invention

In view of this, the present invention provides a rolling mill operating status data processing method, device, computer equipment and medium to solve the problems in the related art of low rolling mill equipment fault diagnosis rate and inaccurate early warning due to interference data in the collected data.

In a first aspect, the present invention provides a method for processing rolling mill operation status data, comprising:

Acquire first vibration data of a vibration monitoring point on the monitored rolling mill;

Determining whether the first vibration data is vibration data in a power-off state;

If the first vibration data does not belong to the vibration data in the power-off state, determining whether the first vibration data belongs to interference data;

If the first vibration data does not belong to the interference data, determining whether a first valid value of the first vibration data is greater than a first threshold; the first threshold is used to determine whether the first vibration data is vibration data when the device is powered on and under load;

If the first effective value of the first vibration data is greater than the first threshold, it is determined that the first vibration data is vibration data in a powered-on, load-bearing state.

The rolling mill operation status data processing method provided by the present invention obtains the first vibration data of the vibration monitoring point on the monitored rolling mill, determines whether the first vibration data belongs to the vibration data in the shutdown state, and when the first vibration data does not belong to the vibration data in the shutdown state, determines whether the first vibration data belongs to the interference data, and when the first vibration data does not belong to the interference data, determines whether the first vibration data is the vibration data in the startup and load state through the relationship between the first effective value of the first vibration data and the first threshold value. The method can screen out the valid data from the collected vibration data and filter out the interference data, so as to reduce the false alarm rate and improve the diagnostic accuracy.

In an optional implementation manner, the determining whether the first vibration data is vibration data in a shutdown state includes:

If the first effective value of the first vibration data is less than a second threshold, the first vibration data and a shutdown tag corresponding to the first vibration data are returned; the second threshold represents vibration data used to determine whether the first vibration data is in a shutdown state.

The rolling mill operation status data processing method provided by the present invention can determine that the first vibration data is the vibration data when the rolling mill is in the shutdown state by judging that the first effective value of the first vibration data is less than the second threshold value, and effectively filters the vibration data collected when the rolling mill is in the shutdown state, thereby indirectly ensuring the collection accuracy of the effective data, which is beneficial to reducing false alarms and making the early warning more accurate.

In an optional embodiment, the method further includes:

If the first vibration data belongs to the interference data, obtaining second vibration data of the vibration monitoring point on the monitored rolling mill;

If the number of times the second vibration data is collected is greater than or equal to the maximum number of times, determining that the second vibration data is interference data;

If the number of times the second vibration data is collected is less than the maximum number of times, a second valid value of the second vibration data is determined, and a label attribute of the second vibration data is judged according to the second valid value; the label attribute includes a power-off label, an interference label, a power-on load label, and a power-on no-load label.

In an optional embodiment, the method further includes:

If the first effective value is less than or equal to the first threshold, acquiring third vibration data of the vibration monitoring point on the monitored rolling mill;

If the number of times the third vibration data is collected is greater than or equal to the maximum number of times, determining that the first vibration data is vibration data when the device is powered on and has no load;

If the number of times the third vibration data is collected is less than the maximum number of times, a third valid value of the third vibration data is determined, and a label attribute of the third vibration data is judged according to the third valid value; the label attribute includes a power-off label, an interference label, a power-on load label, and a power-on no-load label.

The rolling mill operation status data processing method provided by the present invention determines whether to collect multiple vibration data according to the operation status of the rolling mill, and can more accurately judge the label attributes of the vibration data, which is conducive to screening out valid data (i.e., data with load when the machine is started) and filtering out interference data (i.e., external environmental interference and the moment of steel feeding and steel discharge), thereby further improving the accuracy of fault diagnosis of the rolling mill equipment.

In an optional embodiment, the first threshold is determined based on the median and the label coefficient; wherein the median represents the median of the effective values of multiple vibration data with a load label when the machine is turned on, and the label coefficient is used to indicate whether there is a load when the monitored rolling mill is turned on.

In an optional implementation, determining the first threshold based on the median and the label coefficient includes:

D＝K*RMS _m

Where D represents the first threshold, K represents the label coefficient, and RMS _m represents the median.

In an optional implementation manner, determining whether the first vibration data is interference data includes:

Based on the correspondence between the collection time corresponding to the first vibration data and the first vibration data, performing fitting processing on the first vibration data to generate a fitting result;

generating target vibration data based on the fitting result and the first vibration data;

Dividing the target vibration data into a plurality of groups of sub-target vibration data based on the total sampling time and the segmented sampling time of the target vibration data;

Determine the range error value corresponding to each group of sub-target vibration data based on the highest sub-target vibration data and the lowest sub-target vibration data in each group of sub-target vibration data;

Based on a plurality of range error values corresponding one-to-one to the plurality of groups of sub-target vibration data, it is determined whether the first vibration data is interference data.

The rolling mill operation status data processing method provided by the present invention performs fitting processing on the first vibration data to generate a fitting result based on the corresponding relationship between the acquisition time corresponding to the first vibration data and the first vibration data, and generates target vibration data based on the fitting result and the first vibration data, thereby ensuring the accuracy of the generated target vibration data. Then, based on the total sampling time and the segmented sampling time of the target vibration data, the target vibration data is divided into multiple groups of sub-target vibration data, thereby ensuring the accuracy of the obtained multiple groups of segmented target vibration data. Based on the highest sub-target vibration data and the lowest sub-target vibration data in each group of sub-target vibration data, the range error value corresponding to each group of sub-target vibration data is determined, thereby ensuring the accuracy of the range value corresponding to each group of segmented target vibration data calculated. Based on multiple range error values corresponding to the multiple groups of sub-target vibration data, it is judged whether the first vibration data belongs to interference data, thereby ensuring the accuracy of the result of determining that the first vibration data is interference data. The above method can quickly and accurately determine that the first vibration data is interference data, thereby improving the efficiency of determining the interference data, thereby realizing fault diagnosis and fault warning for the monitored rolling mill.

In a second aspect, the present invention provides a rolling mill operation status data processing device, comprising:

A data acquisition module, used for acquiring first vibration data of a vibration monitoring point on the monitored rolling mill;

A shutdown state determination module, used for determining whether the first vibration data is vibration data in a shutdown state;

an interference data judging module, configured to judge whether the first vibration data is interference data if the first vibration data is not vibration data in a power-off state;

A valid value judgment module, used for judging whether a first valid value of the first vibration data is greater than a first threshold value if the first vibration data does not belong to the interference data; the first threshold value is used for judging whether the first vibration data is vibration data when the machine is powered on and under load;

The power-on load state determination module is used to determine that the first vibration data is vibration data in the power-on load state if the first effective value of the first vibration data is greater than a first threshold.

In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the rolling mill operation status data processing method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the rolling mill operating status data processing method of the first aspect or any corresponding embodiment thereof.

BRIEF DESCRIPTION OF THE DRAWINGS

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

1 is a schematic flow chart of a method for processing rolling mill operation status data according to an embodiment of the present invention;

2 is a flow chart of a specific implementation of a method for processing rolling mill operation status data according to an embodiment of the present invention;

3 is a schematic flow chart of another method for processing rolling mill operation status data according to an embodiment of the present invention;

4 is a schematic flow chart of another rolling mill operation status data processing method according to an embodiment of the present invention;

5 is a schematic flow chart of another method for processing rolling mill operation status data according to an embodiment of the present invention;

6 is a structural block diagram of a rolling mill operation status data processing device according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention.

DETAILED DESCRIPTION

In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

Since a rolling mill generally has multiple states during operation, namely, the power-off state, the load state, the no-load state, and the instantaneous state of steel feeding and steel tapping, etc., in the online automatic monitoring process of the rolling mill, more attention is generally paid to the load state. There are two situations of no-load state: one is a long period of no-load state; the other is a short period of time during the continuous rolling of multiple steel bars, when the front steel bar rolls out of the rolling mill and the rear steel bar has not yet entered the rolling mill. Therefore, a method is needed to identify the operating state of the rolling mill, avoid collecting the data of the second type of no-load state, and avoid collecting the data of steel feeding and steel tapping.

According to an embodiment of the present invention, an embodiment of a method for processing rolling mill operating status data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

In this embodiment, a method for processing rolling mill operation status data is provided. FIG. 1 is a flow chart of the method for processing rolling mill operation status data according to an embodiment of the present invention. As shown in FIG. 1 , the process includes the following steps:

Step S101, obtaining first vibration data of a vibration monitoring point on a monitored rolling mill.

Specifically, there may be one or more vibration monitoring points on the monitored rolling mill, which may be arranged at different parts of the monitored rolling mill; the first vibration data may be vibration acceleration data, and the vibration acceleration data of the corresponding vibration monitoring points may be collected by using acceleration sensors arranged at the corresponding vibration monitoring points on the monitored rolling mill. The operating status of the monitored rolling mill (for example, shutdown and power outage, startup with load, startup without load, the moment of steel feeding and outlet, etc.) may be judged by collecting the vibration data of the vibration monitoring points on the monitored rolling mill.

Step S102, determining whether the first vibration data is vibration data in a power-off state.

Specifically, before determining whether the first vibration data belongs to the vibration data when the monitored rolling mill is in the shutdown state, the first effective value of the first vibration data can be determined by the following formula:

Here, RMS represents the first effective value of the first vibration data, _Xi represents the first vibration data, n represents the total number of the first vibration data, and i represents the sequence number of the first vibration data.

Step S102 also includes step S1021:

Step S1021, if the first effective value of the first vibration data is less than the second threshold, the first vibration data and the shutdown label corresponding to the first vibration data are returned; the second threshold represents the vibration data used to determine whether the first vibration data is in the shutdown state.

Specifically, as shown in FIG2 , after determining the first effective value RMS of the first vibration data, it is possible to determine whether the first vibration data is the vibration data when the monitored rolling mill is in the shutdown state by comparing the first effective value RMS of the first vibration data with the second threshold value C, that is: when the first effective value RMS is less than the second threshold value C, that is, RMS<C, it is determined that the first vibration data is the vibration data when the monitored rolling mill is in the shutdown state, and the first vibration data and the shutdown tag corresponding to the first vibration data are returned to the cloud; the shutdown tag is used to indicate that the first vibration data is the vibration data detected when the rolling mill is in the shutdown state. Among them, the second threshold value C is a threshold value used to determine whether the rolling mill is shut down. If it is lower than the C value, it is considered that the rolling mill is in the shutdown state, and if it is higher than the C value, it is considered that the rolling mill is in the start state. The value range of C can be [0.1, 0.3]. When the environmental interference is not large, after the rolling mill equipment is shut down, the effective value of its vibration acceleration is usually between 0.01m/ ^s2 and 0.03m/ ^s2 , while the effective value of the vibration acceleration after starting up is usually greater than 0.5m/ ^s2 . However, if there is a large external noise, the C value can be increased depending on the actual situation.

Step S103: if the first vibration data is not vibration data in the power-off state, determining whether the first vibration data is interference data.

Specifically, as shown in FIG. 2 , when the first effective value RMS of the first vibration data is greater than or equal to the second threshold value C, that is, RMS ≥ C, it is necessary to determine whether the first vibration data is interference data.

Step S104, if the first vibration data does not belong to the interference data, determine whether the first effective value of the first vibration data is greater than a first threshold; the first threshold is used to determine whether the first vibration data is vibration data when the machine is powered on and in a load state.

Specifically, the first threshold is determined based on the median and the label coefficient, as shown in the following formula:

D＝K*RMS _m

Wherein, D represents the first threshold value, K represents the label coefficient, and RMS _m represents the median. The label coefficient K is used to indicate whether the monitored rolling mill is loaded when it is turned on, and is usually taken as 0.5, because the effective value of the vibration acceleration is usually more than twice that of the unloaded state when the machine is turned on with load. The label coefficient K can also be fine-tuned up and down according to the actual situation on site. The median RMS _m represents the median of the effective values of multiple vibration data with the label of turned on with load, for example: pre-acquire the effective value array {RMS ₁ , RMS ₂ , RMS ₃ , ..., RMS _N } of the previous N vibration data that have been marked as the label of turned on with load, and calculate the median RMS _m of its effective value array.

More specifically, as shown in FIG. 2 , when the first vibration data is not interference data, it can be determined whether the first vibration data is vibration data in a powered-on state according to the magnitude relationship between the first effective value RMS of the first vibration data and the first threshold D (ie, K*RMS _m ).

Step S105: if the first effective value of the first vibration data is greater than a first threshold, determining that the first vibration data is vibration data in a powered-on, load-bearing state.

Specifically, as shown in Figure 2, when the first effective value RMS of the first vibration data is greater than the first threshold D, that is, RMS>K*RMS _m , it can be determined that the first vibration data is vibration data when the power-on and load state is on, and the first vibration data and the corresponding power-on and load label are returned to the cloud.

In some optional implementations, as shown in FIG3 , after the above step S103, the method further includes:

Step S301: if the first vibration data belongs to the interference data, obtaining second vibration data of the vibration monitoring point on the monitored rolling mill.

Specifically, when the first vibration data is interference data, it is necessary to collect vibration data of the vibration monitoring point on the monitored rolling mill to obtain the second vibration data.

Step S302: If the number of times the second vibration data is collected is greater than or equal to the maximum number of times, determining that the second vibration data is interference data.

Specifically, the vibration data is collected according to the collection times Count, and data collection can be performed from Count=1, the maximum collection times is Count _m , and each data collection will increase the collection times by one, that is, Count=Count+1; when the collection times of the second vibration data is greater than or equal to the maximum collection times, that is, Count≥Count _m , the second vibration data is determined to be interference data, and the second vibration data and the corresponding interference label are returned.

Step S303, if the number of times the second vibration data is collected is less than the maximum number of times, determine the second valid value of the second vibration data, and judge the label attribute of the second vibration data according to the second valid value; the label attribute includes a power-off label, an interference label, a power-on load label, and a power-on no-load label.

Specifically, as shown by arrow “1” in FIG. 2 , when the number of times the second vibration data is collected is less than the maximum number of times, ie, Count<Count _m , the label attribute of the second vibration data will be determined again according to the above steps S101 to S105 .

In some optional implementations, as shown in FIG4 , after the above step S104, the method further includes:

Step S401: if the first effective value is less than or equal to the first threshold, obtaining third vibration data of the vibration monitoring point on the monitored rolling mill.

Specifically, when the first effective value of the first vibration data is less than or equal to the first threshold, that is, RMS≤D, it is necessary to collect vibration data of the vibration monitoring point on the monitored rolling mill to obtain third vibration data.

Step S402: If the number of times the third vibration data is collected is greater than or equal to the maximum number of times, it is determined that the first vibration data is vibration data in a powered-on, no-load state.

Specifically, when the number of collections of the third vibration data is greater than or equal to the maximum number of collections, ie, Count≥Count _m , the second vibration data is determined to be vibration data in a powered-on no-load state, and the second vibration data and the corresponding powered-on no-load tag are returned.

Step S403, if the number of times the third vibration data is collected is less than the maximum number of times, determine the third valid value of the third vibration data, and judge the label attribute of the third vibration data according to the third valid value; the label attribute includes a power-off label, an interference label, a power-on load label, and a power-on no-load label.

Specifically, as shown by arrow “2” in FIG. 2 , when the number of collection times of the third vibration data is less than the maximum number of collection times, ie, Count<Count _m , it is necessary to re-determine the label attribute of the second vibration data according to the above steps S101 to S105 .

In some optional implementations, as shown in FIG5 , the above step S103 further includes:

Step S501 : performing fitting processing on the first vibration data based on the corresponding relationship between the collection time corresponding to the first vibration data and the first vibration data, and generating a fitting result.

Specifically, the fitting result may be a fitting curve, and the specific implementation method of the fitting process may be set according to actual conditions, and is not specifically limited here.

Step S502: generating target vibration data based on the fitting result and the first vibration data.

Specifically, the fitting vibration data corresponding to each sampling time is determined in the fitting curve, and then the fitting vibration data is subtracted from the first vibration data corresponding to each sampling time to obtain the target vibration data.

Step S503 : dividing the target vibration data into a plurality of groups of sub-target vibration data based on the total sampling time and the segmented sampling time of the target vibration data.

Specifically, the total sampling time and segmented sampling time of the target vibration data input by the user or sent by other devices can be received by the electronic device, and then the total sampling time is divided by the segmented sampling time and rounded up to obtain the number of groups corresponding to the segmented target vibration data; finally, the target vibration data is grouped according to the segmented sampling time; when the sampling time corresponding to the last group of segmented target vibration data is less than the segmented sampling time, a segmented fixed-duration period of target vibration data is collected starting from the last data of the target vibration data as the last group of segmented target vibration data.

Step S504: Based on the highest sub-target vibration data and the lowest sub-target vibration data in each group of sub-target vibration data, a range error value corresponding to each group of sub-target vibration data is determined. Specifically, the range error value can be understood as a range value.

Step S505 , judging whether the first vibration data is interference data based on a plurality of range error values corresponding one-to-one to the plurality of groups of sub-target vibration data.

Specifically, in the process of determining whether the first vibration data is interference data, each range value can be compared. When the maximum range between each range value exceeds the preset range, the first vibration data is determined to be interference data; when the maximum range between each range value does not exceed the preset range value, the first vibration data is determined not to be interference data.

In some optional implementations, as shown in FIG. 2 , the present invention further provides a specific implementation of the operation status data processing method, which is as follows:

Step 1, set the current batch collection times Count=1, and set the maximum collection times Count _m ;

Step 2, collecting vibration data of the corresponding vibration monitoring point by means of a vibration acceleration sensor arranged at the vibration monitoring point of the monitored rolling mill, which is denoted as S;

Step 3, calculating the effective value RMS of the vibration data;

Step 4: Let C be the threshold for determining whether to shut down. If RMS < C, return the original vibration data S and the shutdown tag to the cloud and end. Otherwise, continue to perform the following steps:

Step 5: segment the vibration data, identify external environmental interference or steel feeding and steel discharge moments, and classify them as interference data. If the identification result does not belong to interference data, proceed to step 6, otherwise set Count = Count + 1, if Count < Count _m , restart from step 2; if Count ≥ Count _m , return the original vibration data S and interference label to the cloud and end;

Step 6, obtain the effective value array {RMS ₁ ,RMS ₂ ,RMS ₃ ,...,RMS _N } of the previous N vibration data marked as powered on with load, and calculate the median, which is set as RMS _m ;

Step 7, let K be the coefficient for judging whether there is load when the machine is turned on. If RMS>K*RMS _m , return the original vibration data S and the label of the machine being loaded to the cloud and end; otherwise, let Count＝Count+1, if Count<Count _m , restart from step 2; if Count≥Count _m , return the original vibration data S and the label of the machine being unloaded to the cloud and end.

In this embodiment, a rolling mill operation status data processing device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and/or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

This embodiment provides a rolling mill operation status data processing device, as shown in FIG6 , comprising:

A data acquisition module 601 is used to acquire first vibration data of a vibration monitoring point on a monitored rolling mill;

A shutdown state determination module 602, used to determine whether the first vibration data is vibration data in a shutdown state;

An interference data judging module 603, configured to judge whether the first vibration data is interference data if the first vibration data is not vibration data in a power-off state;

The effective value judgment module 604 is used to judge whether the first effective value of the first vibration data is greater than a first threshold if the first vibration data does not belong to the interference data; the first threshold is used to judge whether the first vibration data is vibration data when the machine is powered on and under load;

The power-on load state determining module 605 is used to determine that the first vibration data is vibration data in the power-on load state if the first effective value of the first vibration data is greater than a first threshold.

In some optional implementations, the shutdown state determination module 602 includes:

A shutdown label determination unit is used to return the first vibration data and the shutdown label corresponding to the first vibration data if the first valid value of the first vibration data is less than a second threshold; the second threshold represents the vibration data used to determine whether the first vibration data is in a shutdown state.

In some optional embodiments, the device further comprises:

a second vibration data acquisition unit, configured to acquire second vibration data of a vibration monitoring point on the monitored rolling mill if the first vibration data belongs to the interference data;

an interference data determining unit, configured to determine that the second vibration data is interference data if the number of times the second vibration data is collected is greater than or equal to a maximum number of times;

The first tag attribute determination unit is used to determine a second valid value of the second vibration data if the number of collection times of the second vibration data is less than the maximum number of collection times, and judge the tag attribute of the second vibration data according to the second valid value; the tag attribute includes a power-off tag, an interference tag, a power-on load tag, and a power-on no-load tag.

In some optional embodiments, the device further comprises:

a third vibration data acquisition unit, configured to acquire third vibration data of the vibration monitoring point on the monitored rolling mill if the first effective value is less than or equal to the first threshold;

a power-on no-load determination unit, configured to determine that the first vibration data is vibration data in a power-on no-load state if the number of collection times of the third vibration data is greater than or equal to a maximum number of collection times;

The second label attribute determination unit is used to determine the third valid value of the third vibration data if the number of collection times of the third vibration data is less than the maximum number of collection times, and judge the label attribute of the third vibration data according to the third valid value; the label attribute includes a power-off label, an interference label, a power-on load label and a power-on no-load label.

In some optional embodiments, the first threshold is determined based on the median and the label coefficient; wherein the median represents the median of the effective values of multiple vibration data with a load label when the machine is turned on, and the label coefficient is used to indicate whether there is a load when the monitored rolling mill is turned on.

In some optional implementations, determining the first threshold based on the median and the label coefficient includes:

D＝K*RMS _m

Where D represents the first threshold, K represents the label coefficient, and RMS _m represents the median.

In some optional implementations, the interference data determination module 603 includes:

a fitting processing unit, configured to perform fitting processing on the first vibration data based on a corresponding relationship between an acquisition time corresponding to the first vibration data and the first vibration data, and generate a fitting result;

a target vibration data generating unit, configured to generate target vibration data based on the fitting result and the first vibration data;

A data division unit, configured to divide the target vibration data into a plurality of groups of sub-target vibration data based on a total sampling time and a segmented sampling time of the target vibration data;

A range error value determination unit, used to determine the range error value corresponding to each group of sub-target vibration data based on the highest sub-target vibration data and the lowest sub-target vibration data in each group of sub-target vibration data;

The interference data judging unit is used to judge whether the first vibration data is interference data based on a plurality of range error values corresponding one-to-one to the plurality of groups of sub-target vibration data.

The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

An embodiment of the present invention further provides a computer device having the rolling mill operation status data processing device shown in FIG. 6 above.

Please refer to Figure 7, which is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention. As shown in Figure 7, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of the GUI on an external input/output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and/or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). In Figure 7, a processor 10 is taken as an example.

The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims (9)

1. A method for processing rolling mill operation status data, characterized in that the method comprises: Acquire first vibration data of a vibration monitoring point on the monitored rolling mill; Determining whether the first vibration data is vibration data in a power-off state; If the first vibration data does not belong to the vibration data in the power-off state, determining whether the first vibration data belongs to interference data; If the first vibration data does not belong to the interference data, determining whether a first valid value of the first vibration data is greater than a first threshold; the first threshold is used to determine whether the first vibration data is vibration data when the device is powered on and in a load state; If the first effective value of the first vibration data is greater than the first threshold, determining that the first vibration data is vibration data when the device is powered on and in a load state; Determining whether the first vibration data is interference data includes: Based on the correspondence between the collection time corresponding to the first vibration data and the first vibration data, performing fitting processing on the first vibration data to generate a fitting result; generating target vibration data based on the fitting result and the first vibration data; Dividing the target vibration data into a plurality of groups of sub-target vibration data based on the total sampling time and the segmented sampling time of the target vibration data; Determine the range error value corresponding to each group of sub-target vibration data based on the highest sub-target vibration data and the lowest sub-target vibration data in each group of sub-target vibration data; Based on a plurality of range error values corresponding one-to-one to the plurality of groups of sub-target vibration data, it is determined whether the first vibration data is interference data. 2. The method according to claim 1, characterized in that the step of determining whether the first vibration data is vibration data in a shutdown state comprises: If the first effective value of the first vibration data is less than a second threshold, the first vibration data and a shutdown tag corresponding to the first vibration data are returned. 3. The method according to claim 1 or 2, characterized in that the method further comprises: If the first vibration data belongs to the interference data, obtaining second vibration data of the vibration monitoring point on the monitored rolling mill; If the number of times the second vibration data is collected is greater than or equal to the maximum number of times, determining that the second vibration data is interference data; If the number of times the second vibration data is collected is less than the maximum number of times, the second valid value of the second vibration data is determined, and the label attribute of the second vibration data is judged according to the second valid value; the label attribute includes a power-off label, an interference label, a power-on load label, and a power-on no-load label. 4. The method according to claim 1 or 2, characterized in that the method further comprises: If the first effective value is less than or equal to the first threshold, acquiring third vibration data of the vibration monitoring point on the monitored rolling mill; If the number of times the third vibration data is collected is greater than or equal to the maximum number of times, determining that the first vibration data is vibration data when the device is powered on and has no load; If the number of times the third vibration data is collected is less than the maximum number of times, a third valid value of the third vibration data is determined, and a label attribute of the third vibration data is judged according to the third valid value; the label attribute includes a power-off label, an interference label, a power-on load label, and a power-on no-load label. 5. The method according to claim 1 is characterized in that the first threshold is determined based on the median and the label coefficient; wherein the median represents the median of the effective values of multiple vibration data with a load label when the machine is turned on, and the label coefficient is used to indicate whether there is a load when the monitored rolling mill is in the turned-on state. 6. The method according to claim 5, characterized in that determining the first threshold based on the median and the label coefficient comprises: D＝K*RMS _m Where D represents the first threshold, K represents the label coefficient, and RMS _m represents the median. 7. A rolling mill operation status data processing device, characterized in that the device comprises: A data acquisition module, used for acquiring first vibration data of a vibration monitoring point on the monitored rolling mill; A shutdown state determination module, used for determining whether the first vibration data is vibration data in a shutdown state; an interference data judging module, configured to judge whether the first vibration data is interference data if the first vibration data is not vibration data in a power-off state; A valid value judgment module, used for judging whether a first valid value of the first vibration data is greater than a first threshold value if the first vibration data does not belong to the interference data; the first threshold value is used for judging whether the first vibration data is vibration data when the machine is powered on and under load; a power-on load state determination module, configured to determine that the first vibration data is vibration data when the machine is in a power-on load state if the first effective value of the first vibration data is greater than a first threshold value; The interference data judgment module includes: a fitting processing unit, configured to perform fitting processing on the first vibration data based on a corresponding relationship between an acquisition time corresponding to the first vibration data and the first vibration data, and generate a fitting result; a target vibration data generating unit, configured to generate target vibration data based on the fitting result and the first vibration data; A data division unit, configured to divide the target vibration data into a plurality of groups of sub-target vibration data based on a total sampling time and a segmented sampling time of the target vibration data; A range error value determination unit, used to determine the range error value corresponding to each group of sub-target vibration data based on the highest sub-target vibration data and the lowest sub-target vibration data in each group of sub-target vibration data; The interference data judging unit is used to judge whether the first vibration data is interference data based on a plurality of range error values corresponding one-to-one to the plurality of groups of sub-target vibration data. 8. A computer device, comprising: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the rolling mill operation status data processing method according to any one of claims 1 to 6 by executing the computer instructions. 9. A computer-readable storage medium, characterized in that computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to enable a computer to execute the rolling mill operation status data processing method according to any one of claims 1 to 6.