Data processing method for intelligently controlling sea cucumber processing system

Abstract

The invention relates to the technical field of control and regulation, in particular to a data processing method for intelligently controlling a sea cucumber processing system, which comprises the following steps: acquiring dimension data of different preset dimensions of different preset links of the sea cucumber processing system in a current time period, and equally dividing the current time period; determining an abnormal situation feature value of each preset dimension under each target sub-segment; screening out a target abnormal dimension of each preset link under each target sub-segment; determining an abnormal characteristic value of each preset link under each target sub-segment; screening out a target abnormal link corresponding to each target sub-segment; determining a comprehensive abnormal characterization quantity corresponding to each preset link; and determining a current operation state evaluation value corresponding to the sea cucumber processing system. According to the method, the data of different dimensions in the current time period is analyzed, so that the operation condition of the sea cucumber processing system is evaluated, and the rationality of evaluating the operation condition of the sea cucumber processing system is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of control adjustment, and in particular to a data processing method for intelligently controlling a sea cucumber processing system. BACKGROUND

[0002] As a kind of echinoderm living in the sea, sea cucumber is not only an important part of marine ecosystem, but also a kind of nutritious tonic product favored by people. However, fresh sea cucumber is not easy to preserve, and is usually processed into dried sea cucumber, instant sea cucumber, sea cucumber peptide and other products through a sea cucumber processing system. In order to ensure the quality of sea cucumber processing, the running condition of the sea cucumber processing system needs to be monitored in the sea cucumber processing process so as to monitor abnormal running conditions in time. At present, when the running condition is evaluated through a data processing method, the method usually adopted is as follows: monitoring data at the current time is collected through a sensor, and the running condition is evaluated based on the abnormal condition of the monitoring data collected at the current time.

[0003] However, when the running condition of the sea cucumber processing system is evaluated based on the abnormal condition of the monitoring data collected at the current time, the following technical problems often exist: In actual conditions, a sensor may be subject to instantaneous electromagnetic interference, vibration or occasional errors in reading transmission, resulting in serious distortion of a certain data point. Therefore, the monitoring data collected at the current time may not represent the real condition of the sea cucumber processing system, thereby resulting in poor rationality of evaluating the running condition of the sea cucumber processing system. SUMMARY

[0004] In order to solve the technical problem of poor rationality of evaluating the running condition of the sea cucumber processing system, the present application provides a data processing method for intelligently controlling a sea cucumber processing system.

[0005] In the first aspect, the present application provides a data processing method for intelligently controlling a sea cucumber processing system, which comprises: acquiring dimension data of different preset dimensions of different preset links of the sea cucumber processing system in a current time period, and equally dividing the current time period to obtain a target sub-period; determining an abnormal situation feature value of each preset dimension in each target sub-period according to the distribution of the dimension data of each preset dimension in each target sub-period; selecting a target abnormal dimension of each preset link in each target sub-period from all preset dimensions according to the abnormal situation feature value; determining an abnormal feature value of each preset link in each target sub-period according to the related condition of the dimension data between the target abnormal dimension in the target sub-period and other target abnormal dimensions in the target sub-period; According to the abnormal characteristic value, a target abnormal link corresponding to each target sub-section is screened out from all preset links; According to the abnormal distribution of each preset link in the preset dimension under different target sub-sections, a comprehensive abnormal characteristic quantity corresponding to each preset link is determined. According to the comprehensive abnormal characteristic quantity corresponding to all preset links, a current running condition evaluation value corresponding to the marine working system is determined.

[0006] In combination with the first aspect, in a possible implementation manner, the determination of the abnormal trend characteristic value of each preset dimension under each target sub-section according to the distribution of the dimension data of each preset dimension within each target sub-section comprises: Any one of the preset links is determined as a marker link, any one of the preset dimensions of the marker link is determined as a marker dimension, and any one of the target sub-sections is determined as a marker sub-section; The theoretical standard value corresponding to the marker dimension is obtained as a marker theoretical standard value; The dimension data of the marker dimension within a historical running time period of the marine working system is obtained; The mean value of all dimension data of the marker dimension obtained within the historical running time period is determined as a marker actual standard value; The data reference range of the marker dimension is constructed according to the marker theoretical standard value and the marker actual standard value; If the dimension data of the marker dimension does not belong to the data reference range, the dimension data of the marker dimension is determined as error data; According to the situation that each error data of the marker dimension exceeds the data reference range, an initial deviation factor corresponding to each error data of the marker dimension is determined; According to the number of error data of the marker dimension within the marker sub-section, the accumulated value of the initial deviation factors corresponding to all error data of the marker dimension within the marker sub-section, and the number of extreme values in the fitting curve formed by all error data of the marker dimension within the marker sub-section, the abnormal trend characteristic value of the marker dimension under the marker sub-section is determined.

[0007] In combination with the first aspect, in a possible implementation manner, the construction of the data reference range of the marker dimension according to the marker theoretical standard value and the marker actual standard value comprises: The absolute value of the difference between the marker theoretical standard value and the marker actual standard value is determined as the allowable fluctuation error of the marker dimension; The marker theoretical standard value is taken as a middle value, and the allowable fluctuation error is taken as a step size to construct the data reference range of the marker dimension.

[0008] With reference to the first aspect, in a possible implementation manner, the determining, according to a case that each error data in the marking dimension exceeds the data reference range, an initial deviation factor corresponding to each error data in the marking dimension, comprises: determining any one error data in the marking dimension as a marking error data; if the marking error data is greater than a maximum value of the data reference range, determining a difference between the marking error data and the maximum value of the data reference range as the initial deviation factor corresponding to the marking error data; if the marking error data is less than a minimum value of the data reference range, determining a difference between the minimum value of the data reference range and the marking error data as the initial deviation factor corresponding to the marking error data.

[0009] With reference to the first aspect, in a possible implementation manner, the screening, according to the abnormal state feature value, a target abnormal dimension of each preset link in each target subsegment from all preset dimensions, comprises: determining any one preset link as a marking link, any one preset dimension of the marking link as a marking dimension, and any one target subsegment as a marking subsegment; if an abnormal state feature value of the marking dimension in the marking subsegment is greater than a preset dimension abnormal threshold value, determining the marking dimension as a target abnormal dimension of the marking link in the marking subsegment.

[0010] With reference to the first aspect, in a possible implementation manner, the determining, according to a dimension data correlation case between the target abnormal dimension in each target subsegment and other target abnormal dimensions in the target subsegment, an abnormal feature value of each preset link in each target subsegment, comprises: determining, according to a dimension data correlation case between each target abnormal dimension in each target subsegment and other target abnormal dimensions in the target subsegment, an initial abnormal feature factor corresponding to each target abnormal dimension of each preset link in each target subsegment; determining, according to the initial abnormal feature factor corresponding to each target abnormal dimension of each preset link in each target subsegment and an abnormal state feature value of the target abnormal dimension in the target subsegment, a target abnormal feature factor corresponding to each target abnormal dimension of each preset link in each target subsegment; determining, according to a mean value of the target abnormal feature factors corresponding to all target abnormal dimensions of each preset link in each target subsegment and a number of target abnormal dimensions of each preset link in each target subsegment, an abnormal feature value of each preset link in each target subsegment.

[0011] With reference to the first aspect above, in a possible implementation manner, the determining, according to a dimensional data correlation condition of each target abnormal dimension of each target sub-segment within the target sub-segment with other target abnormal dimensions, of an initial abnormal characteristic factor corresponding to each target abnormal dimension of each preset link in each target sub-segment, comprises: determining any one preset link as a marked link, and determining any one target sub-segment as a marked sub-segment; determining any one target abnormal dimension of the marked link in the marked sub-segment as a marked abnormal dimension, and determining each target abnormal dimension of the marked link in the marked sub-segment except the marked abnormal dimension as a reference abnormal dimension; constructing all dimensional data of the marked abnormal dimension within the marked sub-segment as a marked dimensional data sequence of the marked abnormal dimension in the marked sub-segment; constructing all dimensional data of each reference abnormal dimension within the marked sub-segment as a reference dimensional data sequence of each reference abnormal dimension in the marked sub-segment; determining an absolute value of a Pearson correlation coefficient between the marked dimensional data sequence and each reference dimensional data sequence as a reference correlation index; determining a mean value of all reference correlation indexes as the initial abnormal characteristic factor corresponding to the marked abnormal dimension of the marked link in the marked sub-segment.

[0012] With reference to the first aspect above, in a possible implementation manner, the screening, according to the abnormal characteristic value, of a target abnormal link corresponding to each target sub-segment from all preset links comprises: determining any one preset link as a marked link, and determining any one target sub-segment as a marked sub-segment; if the abnormal characteristic value of the marked link in the marked sub-segment is greater than a preset link abnormal threshold value, determining the marked link as the target abnormal link corresponding to the marked sub-segment.

[0013] With reference to the first aspect above, in a possible implementation manner, the determining, according to an abnormal distribution condition of a preset dimension of each preset link in different target sub-segments, of a comprehensive abnormal representation quantity corresponding to each preset link comprises: if an abnormal trend characteristic value of the preset dimension in a target sub-segment is greater than a preset sub-segment abnormal threshold value, determining the target sub-segment as a dimensional abnormal sub-segment corresponding to the preset dimension; determine a local anomaly representation corresponding to each preset dimension according to the mean value of the anomaly trend characteristic value of each preset dimension under all the dimension anomaly sub-sections corresponding thereto, the number of the dimension anomaly sub-sections corresponding to each preset dimension, and the time interval between the first dimension anomaly sub-section and the last dimension anomaly sub-section corresponding to each preset dimension; if the anomaly characteristic value of the preset link under the target sub-section is greater than the preset sub-section anomaly threshold value, the target sub-section is determined as a link anomaly sub-section corresponding to the preset link; determine a dimension anomaly sub-section set corresponding to each preset dimension from the set of all the dimension anomaly sub-sections corresponding to each preset dimension; determine a comprehensive anomaly representation corresponding to each preset link according to the mean value of the local anomaly representations corresponding to all the preset dimensions of each preset link, the number of the link anomaly sub-sections corresponding to each preset link, and the number of elements in the intersection of the dimension anomaly sub-section sets corresponding to all the preset dimensions of each preset link.

[0014] In combination with the first aspect, in a possible implementation manner, the determining of the current operation condition evaluation value corresponding to the marine working system according to the comprehensive anomaly representations corresponding to all the preset links comprises: determine an overall anomaly sub-section from each dimension anomaly sub-section in the intersection of the dimension anomaly sub-section sets corresponding to all the preset dimensions of all the preset links; determine the current operation condition evaluation value corresponding to the marine working system according to the mean value of the comprehensive anomaly representations corresponding to all the preset links, the number of elements in the intersection of the dimension anomaly sub-section sets corresponding to all the preset dimensions of all the preset links, and the mean value of the anomaly trend characteristic values of all the preset dimensions of all the preset links under all the overall anomaly sub-sections.

[0015] In the second aspect, the present application provides a data processing device for intelligently controlling a marine working system, the device comprising: an acquisition and equalization module configured to acquire dimension data of different preset dimensions of different preset links of the marine working system in a current time period, and to equally divide the current time period to obtain target sub-sections; an anomaly trend characteristic value determination module configured to determine an anomaly trend characteristic value of each preset dimension under each target sub-section according to the distribution of the dimension data of each preset dimension in each target sub-section; an anomaly dimension screening module configured to screen target anomaly dimensions of each preset link under each target sub-section from all the preset dimensions according to the anomaly trend characteristic value; Anomaly characteristic value determination module, configured to determine an anomaly characteristic value of each preset link in each target sub-section according to a dimensional data correlation between the target anomaly dimension under each target sub-section and other target anomaly dimensions in the target sub-section; Anomaly link screening module, configured to screen out a target anomaly link corresponding to each target sub-section from all preset links according to the anomaly characteristic value; Comprehensive anomaly representation quantity determination module, configured to determine a comprehensive anomaly representation quantity corresponding to each preset link according to anomaly distribution of the preset dimension of each preset link in different target sub-sections; Current operation condition evaluation value determination module, configured to determine a current operation condition evaluation value corresponding to the marine working system according to the comprehensive anomaly representation quantity corresponding to all preset links.

[0016] In a third aspect, a server is provided, including a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and run the executable program code from the memory, so that the device executes the method in the first aspect or any possible implementation manner of the first aspect.

[0017] In a fourth aspect, a computer program product is provided, which includes computer program code. When the computer program code runs on a computer, the computer program code causes the computer to execute the method in the first aspect or any possible implementation manner of the first aspect.

[0018] In a fifth aspect, a computer readable storage medium is provided, which stores computer program code. When the computer program code runs on a computer, the computer program code causes the computer to execute the method in the first aspect or any possible implementation manner of the first aspect.

[0019] The present application has the following beneficial effects: The data processing method for intelligently controlling the marine working system provided by the present application realizes the evaluation of the operation condition of the marine working system by analyzing the dimensional data in different dimensions in the current time period, solves the technical problem that the rationality of the operation condition evaluation of the marine working system is poor, and improves the rationality of the operation condition evaluation of the marine working system. Specifically, the dimensional data in different preset dimensions in the current time period obtained by the present application can to some extent represent the real operation condition of the marine working system, which to some extent weakens the influence of accidental data anomalies, and the present application comprehensively considers multiple indexes related to the operation condition, such as anomaly trend characteristic values, anomaly characteristic values and comprehensive anomaly representation quantities, so as to realize the quantification of the current operation condition evaluation value and improve the rationality of the operation condition evaluation of the marine working system. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 any creative work.

[0021] Figure 1 This is a flow chart of a data processing method for an intelligent control sea cucumber processing system according to the present invention; Figure 2 This is a schematic diagram of the structure of a data processing device for an intelligent control system for processing sea cucumbers according to the present invention; Figure 3 The figure is a structural diagram of a computer device of the present invention. DETAILED DESCRIPTION

[0022] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0023] 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.

[0024] refer to Figure 1 , shows the process of some embodiments of a data processing method of an intelligent control sea cucumber processing system of the present invention. The data processing method of the intelligent control sea cucumber processing system includes the following steps: Step S1: obtaining dimension data of different preset dimensions of different preset links of the sea cucumber processing system within the current time period, and dividing the current time period into equal parts to obtain target sub-segments.

[0025] The sea cucumber processing system can be a system for processing sea cucumbers, and can include multiple links. The preset link can be a link included in the sea cucumber processing system. For example, the preset link can be, but is not limited to, a cooking link, a cooling link, and a sterilization link. The number of preset links can be pre-set, which can be 3. The preset dimension can be a pre-set monitoring dimension in different preset links related to the operation of the sea cucumber processing system. Each preset link can include multiple preset dimensions. The number of preset dimensions included in different preset links can be different, and the number of preset dimensions included in the preset link can be pre-set. For example, the preset dimension of the cooking link can be, but is not limited to, a cooking temperature dimension, a steam pressure dimension, and a cooking voltage dimension. The dimension data can be a normalized value of the preset dimension value. For example, the dimension data under the cooking temperature dimension can be a normalized value of the cooking temperature. The current time period can be a time period with the current time as the end time, and the corresponding time length can be 2 hours. The target sub-period can be a sub-time period obtained by equally dividing the current time period. For example, the target sub-period can correspond to a time length of 5 minutes.

[0026] As an example, taking the cooking temperature dimension of the cooking link as an example, in the current time period, the cooking temperature can be collected in real time by the temperature sensor installed in the cooking pot, and the normalized cooking temperature is recorded as the dimension data under the cooking temperature dimension of the cooking link.

[0027] Step S2, according to the distribution of the dimension data of each preset dimension in each target sub-period, determine the abnormal state feature value of each preset dimension in each target sub-period.

[0028] It should be noted that in the processing process of sea cucumbers, each link has its process standard, that is, each parameter of each link has a certain standard, but in actual operation, it is often unavoidable to be affected by various factors, such as changes in environmental temperature and humidity, effects caused by equipment wear and tear, equipment failure, and human major errors. Among them, some factors often cause some small or accidental parameter fluctuations, which can be handled by the system itself or conventional fine-tuning measures, and will not cause substantial damage to the final quality of the product. Some large amplitude parameter fluctuations often mean that there is a more serious problem, which will have a greater impact on product quality, so it is often necessary to analyze the fluctuation of each dimension parameter of each link.

[0029] As an example, this step can include the following steps: First, any one of the preset links is determined as a marked link, and any one of the preset dimensions of the above marked link is determined as a marked dimension, and any one of the target sub-periods is determined as a marked sub-period.

[0030] Secondly, a theoretical standard value corresponding to the marking dimension is obtained as a marking theoretical standard value.

[0031] The theoretical standard value corresponding to the marking dimension can be a value required on the marking dimension when the marine processing system is normally operated.

[0032] For example, a better cooking temperature range when the marine processing system is normally operated is 95-100℃, and the intermediate value of 95-100℃ is 97.5, so the theoretical standard value corresponding to the cooking temperature dimension can be 97.5.

[0033] Thirdly, dimension data of the marking dimension in a historical operation time period of the marine processing system is obtained.

[0034] The historical operation time period can be a time period in which the marine processing system has been normally operated in the past, and the corresponding time length can be one month.

[0035] Fourthly, a mean value of all dimension data of the marking dimension obtained in the historical operation time period is determined as a marking actual standard value.

[0036] Fifthly, a data reference range of the marking dimension can be constructed according to the marking theoretical standard value and the marking actual standard value, which can include the following sub-steps: Firstly, an absolute value of a difference between the marking theoretical standard value and the marking actual standard value is determined as an allowable fluctuation error of the marking dimension.

[0037] Secondly, a data reference range of the marking dimension is constructed with the marking theoretical standard value as a middle value and the allowable fluctuation error as a step length.

[0038] For example, the data reference range of the marking dimension can be wherein A is the marking theoretical standard value, is the allowable fluctuation error of the marking dimension.

[0039] Sixthly, if the dimension data of the marking dimension does not belong to the data reference range, the dimension data of the marking dimension is determined as error data.

[0040] Seventhly, an initial deviation factor corresponding to each error data of the marking dimension can be determined according to a situation that each error data of the marking dimension exceeds the data reference range, which can include the following sub-steps: Firstly, any one error data of the marking dimension is determined as marking error data.

[0041] The second sub-step is to determine the difference between the mark error data and the maximum value of the data reference range as the initial deviation factor corresponding to the mark error data if the mark error data is greater than the maximum value of the data reference range.

[0042] The third sub-step is to determine the difference between the minimum value of the data reference range and the mark error data as the initial deviation factor corresponding to the mark error data if the mark error data is less than the minimum value of the data reference range.

[0043] The eighth step is to determine the abnormal state trend characteristic value of the mark dimension under the mark sub-section according to the number of error data of the mark dimension in the mark sub-section, the cumulative value of the initial deviation factors corresponding to all error data of the mark dimension in the mark sub-section, and the number of extreme values in the fitting curve formed by all error data of the mark dimension in the mark sub-section.

[0044] The fitting curve formed by all error data of the mark dimension in the mark sub-section can be obtained by taking time as the horizontal coordinate and the error data of the mark dimension in the mark sub-section as the vertical coordinate.

[0045] For example, the formula for determining the abnormal state trend characteristic value of the mark dimension under the mark sub-section can be: ; Where B is the abnormal state trend characteristic value of the mark dimension under the mark sub-section. is a normalization function. is the cumulative value of the initial deviation factors corresponding to all error data of the mark dimension in the mark sub-section. b is the number of error data of the mark dimension in the mark sub-section. c is the number of extreme values in the fitting curve formed by all error data of the mark dimension in the mark sub-section.

[0046] It should be noted that when The greater b is, the greater the error data of the marking dimension in the marking sub-section is, and the greater the abnormal data of the marking dimension in the marking sub-section is. The greater c is, the greater the fluctuation of the error data is. For example, a large fluctuation of the cooking water temperature often causes the sea cucumber to experience a sharp change in temperature in a short time, resulting in uneven cooking inside and outside, such as an instant high temperature that can quickly cook the surface of the sea cucumber or even make it focus, while the inside is not yet fully cooked; the subsequent low temperature interrupts the cooking process, which not only seriously affects the taste and texture of the sea cucumber, but also may cause some areas not to be effectively killed, increasing the risk of food safety. Therefore, the greater B is, the more likely there is an abnormality in the marking dimension in the marking sub-section, and the more likely it affects the running state of the system. For example, when the abnormality of the cooking water temperature is large, it often causes the processing effect of the cooking link to deviate from the expected standard, which may result in poor product quality consistency, and the temperature anomaly of the cooking link may affect the stability of the subsequent cooling, sterilization and other links due to the change of the raw material state, thereby reducing the stability of the entire system.

[0047] Step S3: According to the abnormal situation characteristic value, the target abnormal dimension of each target sub-section of each preset link is screened from all preset dimensions.

[0048] As an example, the present step can include the following steps: Firstly, any one of the preset links is determined as a marking link, any one of the preset dimensions of the marking link is determined as a marking dimension, and any one of the target sub-sections is determined as a marking sub-section.

[0049] Secondly, if the abnormal situation characteristic value of the marking dimension in the marking sub-section is greater than the preset dimension abnormal threshold value, the marking dimension is determined as the target abnormal dimension of the marking sub-section of the marking link.

[0050] The preset dimension abnormal threshold value can be a pre-set threshold value, which can be 0.6.

[0051] Step S4: According to the dimension data correlation between the target abnormal dimension of each target sub-section and other target abnormal dimensions in the target sub-section, the abnormal characteristic value of each preset link in each target sub-section is determined.

[0052] As an example, the present step can include the following steps: Firstly, according to the dimension data correlation between each target abnormal dimension of each target sub-section and other target abnormal dimensions in the target sub-section, the initial abnormal characteristic factor corresponding to each target abnormal dimension of each preset link in each target sub-section is determined.

[0053] It should be noted that in the marine processing process, because multiple links are carried out at the same time, in the target sub-section, multiple links of multiple types of data may be abnormal, and the links of the marine processing are closely connected, the output of the previous link is often the input of the next link, and part of the resources and equipment are often shared by multiple links, therefore, there is often a certain correlation between different dimensions.

[0054] For example, determining the initial abnormal characteristic factor corresponding to each target abnormal dimension of each preset link in each target sub-section can include the following sub-steps: First sub-step, determine any one preset link as a marker link, and determine any one target sub-section as a marker sub-section.

[0055] Second sub-step, determine any one target abnormal dimension of the marker link in the marker sub-section as a marker abnormal dimension, and determine each target abnormal dimension of the marker link in the marker sub-section except the marker abnormal dimension as a reference abnormal dimension.

[0056] Third sub-step, all dimension data of the marker abnormal dimension in the marker sub-section form a marker dimension data sequence of the marker abnormal dimension in the marker sub-section.

[0057] Among them, the marker dimension data sequence can be a time sequence.

[0058] Fourth sub-step, all dimension data of each reference abnormal dimension in the marker sub-section form a reference dimension data sequence of each reference abnormal dimension in the marker sub-section.

[0059] Among them, the reference dimension data sequence can be a time sequence.

[0060] Fifth sub-step, the absolute value of the Pearson correlation coefficient between the marker dimension data sequence and each reference dimension data sequence is determined as a reference correlation index.

[0061] Sixth sub-step, the mean value of all reference correlation indexes is determined as the initial abnormal characteristic factor corresponding to the marker abnormal dimension of the marker link in the marker sub-section.

[0062] It should be noted that the larger the initial abnormal characteristic factor corresponding to the marker abnormal dimension, the more likely the marker abnormal dimension is associated with other dimensions in the marker sub-section, the more likely there is a chain effect, and the more likely the marker abnormal dimension causes other dimensions to have abnormal defects in the marker sub-section.

[0063] Secondly, according to the initial abnormal characteristic factor corresponding to each target abnormal dimension of each preset link under each target sub-stage and the abnormal trend characteristic value of the target abnormal dimension under the target sub-stage, the target abnormal characteristic factor corresponding to each target abnormal dimension of each preset link under each target sub-stage is determined.

[0064] For example, the formula corresponding to the determination of the target abnormal characteristic factor corresponding to the target abnormal dimension of the preset link under the target sub-stage can be: ; Wherein, is the target abnormal characteristic factor corresponding to the a-th target abnormal dimension of the i-th preset link under the j-th target sub-stage. i is the serial number of the preset link. j is the serial number of the target sub-stage. a is the serial number of the target abnormal dimension of the i-th preset link under the j-th target sub-stage. is the abnormal trend characteristic value of the a-th target abnormal dimension under the j-th target sub-stage of the i-th preset link under the j-th target sub-stage. is the initial abnormal characteristic factor corresponding to the a-th target abnormal dimension of the i-th preset link under the j-th target sub-stage.

[0065] It should be noted that, The greater, the more likely the a-th target abnormal dimension is associated with other dimensions within the j-th target sub-stage, the more likely there is a chain effect, and the more likely the a-th target abnormal dimension causes other dimensions to have abnormal defects within the j-th target sub-stage. When The greater, the more likely the a-th target abnormal dimension has an abnormality within the j-th target sub-stage, and the more likely it affects the running state of the system. Therefore, when The greater, the greater the abnormal influence caused by the a-th target abnormal dimension within the j-th target sub-stage, and the more likely it affects the running state of the system.

[0066] Thirdly, according to the mean of the target abnormal characteristic factors corresponding to all target abnormal dimensions of each preset link under each target sub-stage and the number of target abnormal dimensions of each preset link under each target sub-stage, the abnormal characteristic value of each preset link under each target sub-stage is determined.

[0067] For example, the formula corresponding to the determination of the abnormal characteristic value of the preset link under the target sub-stage can be: ; Wherein, is the abnormal characteristic value of the i-th preset link under the j-th target sub-stage. i is the serial number of the preset link. j is the serial number of the target sub-stage. is a normalization function. is the number of target abnormal dimensions of the ith preset link under the jth target sub-section. is the number of preset dimensions of the ith preset link. is the mean value of target abnormal characteristic factors corresponding to all target abnormal dimensions of the ith preset link under the jth target sub-section.

[0068] It should be noted that, when is greater, it often indicates that the abnormal influence caused by the ith preset link in the jth target sub-section is greater, and it is more likely to affect the running state of the system. When is greater, it often indicates that the abnormal dimensions of the ith preset link in the jth target sub-section are more, and it often indicates that the ith preset link in the jth target sub-section is more likely to have an abnormal situation. Therefore, when is greater, it often indicates that the abnormal influence caused by the ith preset link in the jth target sub-section is greater, and it is more likely to affect the running state of the system.

[0069] Step S5, according to the abnormal characteristic value, screening out the target abnormal link corresponding to each target sub-section from all preset links.

[0070] As an example, the present step can include the following steps: Firstly, any one preset link is determined as a marker link, and any one target sub-section is determined as a marker sub-section.

[0071] Secondly, if the abnormal characteristic value of the marker link under the marker sub-section is greater than the preset link abnormal threshold value, the marker link is determined as the target abnormal link corresponding to the marker sub-section.

[0072] Among them, the preset link abnormal threshold value can be a threshold value set in advance, which can be 0.7.

[0073] Step S6, according to the abnormal distribution of the preset dimensions of each preset link under different target sub-sections, determining the comprehensive abnormal characteristic quantity corresponding to each preset link.

[0074] As an example, the present step can include the following steps: Firstly, if the abnormal situation characteristic value of the preset dimension under the target sub-section is greater than the preset sub-section abnormal threshold value, the target sub-section is determined as the dimension abnormal sub-section corresponding to the preset dimension.

[0075] Among them, the preset sub-section abnormal threshold value can be a threshold value set in advance, which can be 0.6.

[0076] Secondly, according to the mean of the abnormal state feature values of each preset dimension under all corresponding dimension abnormal sub-sections, the number of dimension abnormal sub-sections corresponding to each preset dimension, and the time interval between the first dimension abnormal sub-section and the last dimension abnormal sub-section corresponding to each preset dimension, the local abnormality characteristic quantity corresponding to each preset dimension is determined.

[0077] For example, the formula for determining the local abnormality characteristic quantity corresponding to the preset dimension can be: ; Wherein, H is the local abnormality characteristic quantity corresponding to the preset dimension. Y is the mean of the abnormal state feature values of the preset dimension under all corresponding dimension abnormal sub-sections. n is the number of dimension abnormal sub-sections corresponding to the preset dimension. is the time interval between the first dimension abnormal sub-section and the last dimension abnormal sub-section corresponding to the preset dimension.

[0078] It should be noted that the larger H is, the more abnormal periods on the preset dimension, the more obvious the abnormal state, and the larger the distribution range, which means that the abnormality of the preset dimension in the current time period is more obvious.

[0079] Thirdly, if the abnormal feature value of the preset link under the target sub-section is greater than the preset sub-section abnormal threshold, the target sub-section is determined as the link abnormal sub-section corresponding to the preset link.

[0080] Fourthly, the set composed of all dimension abnormal sub-sections corresponding to each preset dimension is determined as the dimension abnormal sub-section set corresponding to each preset dimension.

[0081] Fifthly, according to the mean of the local abnormality characteristic quantities corresponding to all preset dimensions of each preset link, the number of link abnormal sub-sections corresponding to each preset link, and the number of elements in the intersection of the dimension abnormal sub-section sets corresponding to all preset dimensions of each preset link, the comprehensive abnormality characteristic quantity corresponding to each preset link is determined.

[0082] For example, the formula for determining the comprehensive abnormality characteristic quantity corresponding to the preset link can be: ; Wherein, is the comprehensive abnormality characteristic quantity corresponding to the i-th preset link. i is the serial number of the preset link. is the number of link abnormal sub-sections corresponding to the i-th preset link. is the number of elements in the intersection of the dimension abnormal sub-section sets corresponding to all preset dimensions of the i-th preset link. is the mean of the local abnormality characteristic quantities corresponding to all preset dimensions of the i-th preset link.

[0083] It should be noted that, when is larger, it often means that the time period of abnormality in the i-th preset link is more. When is larger, it often means that the time period of abnormality in all dimensions in the i-th preset link is more. When is larger, it often means that the abnormality of the preset dimension of the i-th preset link in the current time period is more obvious. Therefore, when is larger, it often means that the number of abnormality of different dimensions in the i-th preset link is more, and the abnormality is larger, which often means that the mutual influence between different data is larger, and the influence on the entire marine engineering system is also larger.

[0084] Step S7, determining the current running condition evaluation value of the marine engineering system according to the comprehensive abnormality characteristic quantity corresponding to all preset links.

[0085] As an example, this step can include the following steps: Firstly, each dimension abnormality sub-segment in the intersection of the dimension abnormality sub-segment set corresponding to all preset dimensions of all preset links is determined as an overall abnormality sub-segment.

[0086] Secondly, according to the mean value of the comprehensive abnormality characteristic quantity corresponding to all preset links, the number of elements in the intersection of the dimension abnormality sub-segment set corresponding to all preset dimensions of all preset links, and the mean value of the abnormality trend characteristic value of all preset dimensions of all preset links under all overall abnormality sub-segments, the current running condition evaluation value of the marine engineering system is determined.

[0087] For example, the formula for determining the current running condition evaluation value of the marine engineering system can be: ; Wherein, F is the current running condition evaluation value of the marine engineering system. is a normalization function. D is the mean value of the comprehensive abnormality characteristic quantity corresponding to all preset links. S is the number of elements in the intersection of the dimension abnormality sub-segment set corresponding to all preset dimensions of all preset links, that is, the number of overall abnormality sub-segments. m is the mean value of the abnormality trend characteristic value of all preset dimensions of all preset links under all overall abnormality sub-segments.

[0088] It should be noted that when D is larger, it often means that the number of simultaneous abnormality of different dimensions in the preset link is more, and the abnormality is larger, and the mutual influence between different data is larger, and the influence on the entire marine working system is larger. When S is larger, it often means that the time period of simultaneous abnormality of all dimensions in the entire marine working system is more. When m is larger, it often means that the entire marine working system is more likely to have abnormality. Therefore, when F is larger, it often means that the running of the marine working system at the current moment is more likely to have abnormality, and it is more necessary to remind the staff to check and maintain.

[0089] Reference Figure 2 Based on the same inventive concept as the above method embodiment, the present application provides a data processing device for intelligently controlling a marine working system, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program implements the steps of the data processing method for intelligently controlling the marine working system when executed by the processor, and can specifically comprise: The acquisition and equalization module 201 is configured to acquire dimension data of different preset dimensions of different preset links of the marine working system in a current time period, and equally divide the current time period to obtain a target sub-period. The abnormal situation characteristic value determination module 202 is configured to determine an abnormal situation characteristic value of each preset dimension in each target sub-period according to the distribution of the dimension data of each preset dimension in each target sub-period. The abnormal dimension screening module 203 is configured to screen out a target abnormal dimension of each target sub-period of each preset link from all preset dimensions according to the abnormal situation characteristic value. The abnormal characteristic value determination module 204 is configured to determine an abnormal characteristic value of each target sub-period of each preset link according to the dimension data correlation between the target abnormal dimension of each target sub-period and other target abnormal dimensions in the target sub-period. The abnormal link screening module 205 is configured to screen out a target abnormal link corresponding to each target sub-period from all preset links according to the abnormal characteristic value. The comprehensive abnormality representation quantity determination module 206 is configured to determine a comprehensive abnormality representation quantity corresponding to each preset link according to the abnormal distribution of the preset dimensions of each preset link in different target sub-periods. The current running condition evaluation value determination module 207 is configured to determine a current running condition evaluation value corresponding to the marine working system according to the comprehensive abnormality representation quantities corresponding to all preset links.

[0090] Figure 3 is a structural schematic diagram of a computer device provided by an embodiment of the present application. For example, Figure 3As shown, the computer device 300 comprises a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein the processor 302 executes the computer program 303, so that the computer device can execute any of the aforementioned data processing methods for intelligently controlling the marine working system.

[0091] Based on the same inventive concept as the above method embodiments, the present application provides a server comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes any of the aforementioned data processing methods for intelligently controlling the marine working system.

[0092] Based on the same inventive concept as the above method embodiments, the present application provides a computer program product comprising computer program code, which, when executed on a computer, causes the computer to execute any of the aforementioned data processing methods for intelligently controlling the marine working system.

[0093] Based on the same inventive concept as the above method embodiments, the present application provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to execute any of the aforementioned data processing methods for intelligently controlling the marine working system.

[0094] In summary, the dimension data of different preset dimensions in the current time period obtained by the present application can represent the real running condition of the marine working system to a certain extent, which to a certain extent weakens the influence of accidental data anomalies, and the present application comprehensively considers multiple indicators related to the running condition, such as abnormal situation characteristic values, abnormal characteristic values, and comprehensive abnormal representation quantities, thereby realizing the quantification of the current running condition evaluation value and improving the rationality of the running condition evaluation of the marine working system.

[0095] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A data processing method for intelligently controlling a sea cucumber processing system, characterized in that: The following steps are involved: Obtain dimensional data of different preset dimensions of different preset links of the sea cucumber processing system within the current time period, and divide the current time period into equal parts to obtain target sub-segments; Determine the abnormal situation characteristic value of each preset dimension in each target sub-segment according to the distribution of the dimension data of each preset dimension in each target sub-segment; According to the abnormal situation feature value, the target abnormal dimension of each preset link under each target sub-segment is screened from all preset dimensions; Determine the abnormal feature value of each preset link in each target subsegment based on the dimensional data correlation between the target abnormal dimension in each target subsegment and other target abnormal dimensions in the target subsegment; According to the abnormal characteristic value, the target abnormal link corresponding to each target sub-segment is screened out from all preset links; Determine the comprehensive abnormality representation corresponding to each preset link based on the abnormal distribution of the preset dimensions under different target sub-segments of each preset link; According to the comprehensive abnormal characterization quantities corresponding to all preset links, the current operating status evaluation value corresponding to the sea cucumber processing system is determined.

2. The data processing method of the intelligent control sea cucumber processing system according to claim 1 is characterized in that: The determining of the abnormal situation characteristic value of each preset dimension in each target subsegment according to the distribution of the dimensional data of each preset dimension in each target subsegment includes: Determine any preset link as a marking link, determine any preset dimension of the marking link as a marking dimension, and determine any target subsegment as a marking subsegment; Obtaining a theoretical standard value corresponding to the marking dimension as the marking theoretical standard value; Obtaining dimension data of the sea cucumber processing system under the marked dimension during a historical operation period; The average value of all dimension data under the marked dimension obtained during the historical operation time period is determined as the actual standard value of the mark; Constructing a data reference range under the marking dimension according to the marking theoretical standard value and the marking actual standard value; If the dimension data under the marked dimension does not belong to the data reference range, the dimension data under the marked dimension is determined as error data; Determining an initial deviation factor corresponding to each error data under the marked dimension according to a situation where each error data under the marked dimension exceeds a data reference range; The abnormal situation characteristic value of the marking dimension in the marking sub-segment is determined based on the number of error data of the marking dimension in the marking sub-segment, the cumulative value of the initial deviation factors corresponding to all error data of the marking dimension in the marking sub-segment, and the number of maximum values ​​in the fitting curve formed by all error data of the marking dimension in the marking sub-segment.

3. The data processing method of the intelligent control sea cucumber processing system according to claim 2 is characterized in that: The step of constructing a data reference range under the marking dimension according to the marking theoretical standard value and the marking actual standard value includes: The absolute value of the difference between the theoretical standard value of the mark and the actual standard value of the mark is determined as the allowable fluctuation error under the mark dimension; The data reference range under the marking dimension is constructed by taking the marking theoretical standard value as the middle value and the allowable fluctuation error as the step size.

4. The data processing method of the intelligent control sea cucumber processing system according to claim 2 is characterized in that: The determining, based on a situation in which each error data under the marked dimension exceeds a data reference range, an initial deviation factor corresponding to each error data under the marked dimension includes: Determine any error data under the marking dimension as marking error data; If the mark error data is greater than the maximum value of the data reference range, determining the difference between the mark error data and the maximum value of the data reference range as the initial deviation factor corresponding to the mark error data; If the mark error data is smaller than the minimum value of the data reference range, the difference between the minimum value of the data reference range and the mark error data is determined as the initial deviation factor corresponding to the mark error data.

5. The data processing method of the intelligent control sea cucumber processing system according to claim 1 is characterized in that: The target abnormal dimension of each preset link under each target sub-segment is screened out from all preset dimensions according to the abnormal situation feature value, including: Determine any preset link as a marking link, determine any preset dimension of the marking link as a marking dimension, and determine any target subsegment as a marking subsegment; If the abnormal situation characteristic value of the marked dimension under the marked sub-segment is greater than the preset dimension abnormality threshold, the marked dimension is determined as the target abnormal dimension of the marking link under the marked sub-segment.

6. The data processing method of the intelligent control sea cucumber processing system according to claim 1 is characterized in that: Determining the abnormal feature value of each preset link in each target subsegment according to the dimensional data correlation between the target abnormal dimension in each target subsegment and other target abnormal dimensions in the target subsegment includes: Determine the initial abnormal feature factor corresponding to each target abnormal dimension in each target subsegment in each preset link according to the dimensional data correlation between each target abnormal dimension in each target subsegment and other target abnormal dimensions in the target subsegment; Determine the target abnormality feature factor corresponding to each target abnormality dimension of each preset link under each target subsegment according to the initial abnormality feature factor corresponding to each target abnormality dimension of each preset link under each target subsegment, and the abnormal situation feature value of the target abnormality dimension under the target subsegment; According to the mean value of the target abnormality feature factors corresponding to all target abnormality dimensions of each preset link under each target sub-segment, and the number of target abnormality dimensions of each preset link under each target sub-segment, the abnormal feature value of each preset link under each target sub-segment is determined.

7. The data processing method of the intelligent control sea cucumber processing system according to claim 6 is characterized in that: The determining of the initial abnormal feature factor corresponding to each target abnormal dimension in each target subsegment of each preset link according to the dimensional data correlation between each target abnormal dimension in each target subsegment and other target abnormal dimensions in the target subsegment includes: Determine any preset link as a marked link, and determine any target subsegment as a marked subsegment; Determine any target abnormal dimension of the marking step under the marking sub-segment as a marked abnormal dimension, and determine each target abnormal dimension of the marking step under the marking sub-segment except the marked abnormal dimension as a reference abnormal dimension; All dimension data of the marked abnormal dimension in the marked sub-segment constitute a marked dimension data sequence of the marked abnormal dimension under the marked sub-segment; All dimension data of each reference abnormal dimension in the marked sub-segment constitute a reference dimension data sequence of each reference abnormal dimension under the marked sub-segment; Determine the absolute value of the Pearson correlation coefficient between the marked dimension data sequence and each reference dimension data sequence as a reference correlation index; The mean value of all reference related indicators is determined as the initial abnormal characteristic factor corresponding to the marked abnormal dimension of the marking link under the marked sub-segment.

8. The data processing method of the intelligent control sea cucumber processing system according to claim 1 is characterized in that: The method of screening out the target abnormal link corresponding to each target sub-segment from all preset links based on the abnormal feature value includes: Determine any preset link as a marked link, and determine any target subsegment as a marked subsegment; If the abnormal characteristic value of the marked link under the marked sub-segment is greater than a preset link abnormality threshold, the marked link is determined as the target abnormal link corresponding to the marked sub-segment.

9. The data processing method of the intelligent control sea cucumber processing system according to claim 1 is characterized in that: Determining the comprehensive abnormality representation corresponding to each preset link according to the abnormality distribution of the preset dimension in different target sub-segments of each preset link includes: If the abnormal situation characteristic value of the preset dimension under the target sub-segment is greater than the preset sub-segment abnormal threshold, the target sub-segment is determined as the dimension abnormal sub-segment corresponding to the preset dimension; Determine the local abnormality representation value corresponding to each preset dimension according to the mean of the abnormal situation characteristic values ​​of each preset dimension under all the corresponding dimensional abnormal sub-segments, the number of dimensional abnormal sub-segments corresponding to each preset dimension, and the time interval between the first dimensional abnormal sub-segment and the last dimensional abnormal sub-segment corresponding to each preset dimension; If the abnormal characteristic value of the preset link under the target sub-segment is greater than the preset sub-segment abnormal threshold, the target sub-segment is determined as the link abnormal sub-segment corresponding to the preset link; Determine a set consisting of all dimension abnormal sub-segments corresponding to each preset dimension as a dimension abnormal sub-segment set corresponding to each preset dimension; The comprehensive abnormality representation corresponding to each preset link is determined based on the mean of the local abnormality representation corresponding to all preset dimensions of each preset link, the number of link abnormality sub-segments corresponding to each preset link, and the number of elements in the intersection of the dimensional abnormality sub-segment sets corresponding to all preset dimensions of each preset link.

10. The data processing method of the intelligent control sea cucumber processing system according to claim 9 is characterized in that: Determining the current operating status evaluation value corresponding to the sea cucumber processing system based on the comprehensive abnormal characterization quantities corresponding to all preset links includes: Determine each dimensional abnormal sub-segment in the intersection of the dimensional abnormal sub-segment sets corresponding to all preset dimensions of all preset links as the overall abnormal sub-segment; The current operating status evaluation value corresponding to the sea cucumber processing system is determined based on the mean value of the comprehensive abnormal characterization quantity corresponding to all preset links, the number of elements in the intersection of the dimensional abnormal sub-segment sets corresponding to all preset dimensions of all preset links, and the mean value of the abnormal situation characteristic values ​​of all preset dimensions of all preset links under all overall abnormal sub-segments.

Images