Industrial production data management method, system and equipment and storage medium

Abstract

The invention provides an industrial production data management method, system and device and a storage medium, and relates to the technical field of big data analysis and processing. The method comprises the steps of obtaining industrial production data and performing redundancy processing on the industrial production data to obtain initial industrial production data; performing data integration on the initial industrial production data by adopting a preset association rule algorithm to obtain precise production data; determining an intelligent early warning index of the industrial production data; and performing multi-source information extraction on the precise production data, and performing early warning management on the industrial production data according to the multi-source information. According to the method, the multi-source characteristic of output data information in the actual industrial production process is fully considered, the data is subjected to integrated processing in combination with the independence and distribution condition of the data, intelligent early warning is performed according to the processed data, an efficient and real data basis is provided for production data early warning, and the production data early warning efficiency is improved. Production data intelligent early warning based on big data is realized, the intelligent early warning efficiency is improved, and safe production is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis and processing, and in particular to an industrial production data management method, system, equipment and storage medium. Background Art

[0002] With the continuous development of information technology, the construction of diversified data systems based on industrial production is gradually accelerating. For information in different application environments and information systems, establishing a reasonable and effective storage, conversion and sharing management mechanism has become one of the most important work contents. Affected by the heterogeneity between data, to some extent, the heterogeneity of data increases the complexity and time cost of accessing related data, which brings certain difficulties to data management.

[0003] At the same time, production data is the most intuitive parameter indicator that reflects the production status. In the intelligent analysis of production data, the safety factor of production data is usually calculated to analyze whether there are any anomalies in the production data. Due to the large base and complex types of production data, this analysis method has the problem of low efficiency of intelligent analysis in practical applications, which makes it impossible to provide efficient and true analysis results for intelligent early warning of production data, resulting in low timeliness of intelligent early warning of production data and failure to ensure safe production. Summary of the invention

[0004] Purpose of the invention: To propose an industrial production data management method, system, equipment and storage medium, which fully considers the multi-source characteristics of the output data information in the actual industrial production process, integrates the data in combination with its own independence and distribution, and performs intelligent early warning based on the processed data, so as to provide an efficient and real data basis for production data early warning, realize intelligent early warning of production data based on big data, improve the efficiency of intelligent early warning, ensure safe production, and effectively solve the above-mentioned problems existing in the prior art.

[0005] In a first aspect of the present invention, a method for managing industrial production data is provided, comprising the following steps:

[0006] S1. Acquire industrial production data, and perform redundancy processing on the industrial production data to obtain initial industrial production data;

[0007] S2. Using a preset association rule algorithm to integrate the initial industrial production data to obtain accurate production data;

[0008] S3. Determine the intelligent early warning index of the industrial production data; wherein the intelligent early warning index is within the safe value range;

[0009] S4. Extract multi-source information from the precise production data, and perform early warning management on the industrial production data based on the multi-source information.

[0010] In a further embodiment of the first aspect, step S1 specifically includes:

[0011] S11. Obtain industrial production data;

[0012] In order to ensure the reliability of subsequent industrial production data integration, the collected real-time data of the industrial production workshop is processed redundantly, mainly to clear the invalid data in the data collection, so as to minimize the granularity of the data collection and transmission stage without affecting the real mapping of the industrial production data. In the specific execution process, the processing of invalid redundant information is implemented based on the correlation fusion of data. Among them, in the industrial production workshop, the physical workshop RFID and environmental sensors present the data of various types of equipment in the form of data streams, which can be expressed as:

[0013] E r (t)=<T,a(t)>

[0014] E s (t)=<S,R(t),D(t)>

[0015] E e (t)=<E,Q(t),W(t)>

[0016] In the formula, E r (t) is the data information in the physical workshop RFID; E s (t) is the data information collected by the environmental sensor; E e (t) is the operating status data information of the production equipment; T is the unique coding information of the RFID tag; a(t) is the number information of the RFID reader and antenna; S is the number information of the environmental sensor; R(t) is the sensing range parameter of the environmental sensor; D(t) is the data information collected by the environmental sensor; E is the equipment number information of the industrial production workshop; Q(t) is the area information of the industrial production workshop equipment; W(t) is the data set parameter of the equipment status of the production workshop; t is the time parameter corresponding to reading the production workshop data;

[0017] S12. By defining the state information, the data in the above formula is described uniformly with the position information, which is expressed as:

[0018] E(t)=<i,loc,∑W(t)>

[0019] Among them, E(t) is the industrial production data after unified description; i is the coding information; loc is the location information. In this way, for any data acquisition device, in any time period, the original data formed is in the above formula. According to the above formula, the state information of the industrial production data can be obtained to determine whether the industrial production data has changed in the future, and further redundancy processing can be performed.

[0020] S13. When the data status does not change, only the data at the start and end times have integration value. Based on this, the invalid data in the time period where the data status does not change is processed. Specifically, it includes:

[0021] S131. Input the industrial production data after unified description, and query the status information according to the code; the industrial production data obtained according to the above formula contains the status information of the data, so the status information can be queried.

[0022] S132, when the state information is consistent, remove the data information; when the state information is inconsistent, return to continue to query the state information according to the code. In this way, the state information can be screened to achieve redundancy processing.

[0023] According to the above method, the current production status is searched according to the data encoding information, and by comparing the corresponding status parameters at different times, it is determined whether it is redundant data, and data preprocessing is achieved, providing a reliable basis for subsequent data integration.

[0024] In a further embodiment of the first aspect, step 2 specifically includes: based on the spatial scale and unit level, extracting the characteristics of the workshop production tasks, combining the elements in the workshop, and describing the state of the entire physical workshop in a dynamic form. Describe the relationship between the production service nodes, and describe the logical relationship of the physical workshop in real time according to the production tasks and plans. At this time, the most direct impact of the dynamic adjustment of the production tasks is that the physical workshop will also change its state accordingly. In addition, data integration is performed according to the spatial scale association rules. Multiple production service nodes composed of spatial objects and the activities between the production service nodes constitute the final physical workshop. This process is as follows:

[0025] S21. According to the initial industrial production data, the production service nodes are refined and divided into flow production service nodes, station production service nodes and cache production service nodes. The relationship between the entire workshop data is expressed as:

[0026] E p (t) = S E +Z E +E E

[0027] Among them, E p (t) is the status data information of the overall physical workshop; S E Provides status data information of mobile production service nodes; Z E Status data information of the workstation production service node; E E To cache the status data information of the production service nodes; the dynamic characteristics of the production service nodes themselves determine that in the physical workshop status data information, the spatial relationship of each production service node also exists in a relatively changing form.

[0028] S22. Use manufacturing tasks to describe the logical relationship between production service nodes. The production data is composed of:

[0029] E p (t) = ∑S Ei +∑Z Ei +ΣE Ei

[0030] Among them, ∑S Ei ,∑Z Ei ,∑E Ei They represent the production data with production task i as the core. After integration through workshop association rules, the data can not only reflect the real situation of the workshop structure, but also accurately describe the task logic. After integrating the production data through the above formula, accurate production data is obtained.

[0031] In a further embodiment of the first aspect, step S3 specifically includes:

[0032] S31. Determine the standard production data intelligent early warning indicators and the safety value range of a single indicator, and construct an early warning comparison data table based on them;

[0033] S32. Compare the calculation results of the production data intelligent early warning indicator change monitoring with the safety value range in the table to determine whether the specific value of the production data intelligent early warning indicator is within the safety value range. That is, after obtaining a data, the data is put into the early warning comparison data table for search, thereby determining whether the data value is within the safety range, so as to determine whether the production situation corresponding to the data is safe.

[0034] In a further embodiment of the first aspect, step S4 specifically includes:

[0035] S41. Under the premise of ensuring that the intelligent early warning indicators of production data are within the safe value range, extract multi-source information of production data, and use the Apache Spark hybrid framework in big data to obtain the peak value of production data when the node displacement is continuous. Based on cloud computing in big data, correct the errors in the intelligent analysis process of production data. Compared with traditional analysis methods, cloud computing based on big data iteratively solves the peak correction coefficient to extract multi-source information of production data. Let the objective function of this process be:

[0036]

[0037] Among them, r is the production data set; V is the production data index weight allocation vector; x is the production data sub-wavelength; I is the normalized assignment of production data index characteristics; R is the importance between multi-source information of production data; n is the correlation between production data; T is the production data assignment instruction;

[0038] S42. According to the above formula, corresponding numerical points are marked in a two-dimensional coordinate system, wherein the X-axis is used as a multi-source information indicator to extract production data, and the Y-axis is used as a precision indicator based on big data analysis to support the extraction of multi-source information of production data through point positions;

[0039] S43. Analyze the multi-source information of production data according to the production data warning level to obtain the warning result; wherein the production data warning level includes yellow warning, orange warning and red warning, and different colors are used to distinguish different levels of predictions. For different danger level warnings, corresponding specific measures are implemented. That is, the calculated multi-source information of production data is put into the production data warning level for comparison, so as to determine the warning level according to the comparison value, such as red alarm.

[0040] In the design of intelligent early warning methods for production data, a mature database is needed to change and manage multi-source information of production data, and directly update all pre-processed production data to the database. When performing a secondary search, the real-time situation of intelligent early warning of production data can be directly judged through historical records. Finally, according to the comparison results, if the value is within the safe value range, no alarm will be processed. Once it exceeds the safe value range, the alarm device will be triggered immediately, realizing intelligent early warning of production data based on big data.

[0041] The second aspect of the present invention proposes an industrial production data management system, which includes four components: an acquisition module, an integration module, a determination module, and an extraction module. Among them, the acquisition module is used to acquire industrial production data, and perform redundancy processing on the industrial production data to obtain initial industrial production data. The integration module is used to perform data integration on the initial industrial production data using a preset association rule algorithm to obtain precise production data. The determination module is used to determine the intelligent early warning index of the industrial production data; wherein the intelligent early warning index is within the safety value range. The extraction module is used to extract multi-source information from the precise production data, and perform early warning management on the industrial production data based on the extracted multi-source information.

[0042] The management system can be used to automatically execute the industrial production data management method disclosed in the first aspect and its further embodiments.

[0043] According to a third aspect of the present invention, an electronic device is provided, comprising a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the industrial production data management method disclosed in the first aspect and its further embodiments is implemented.

[0044] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, in which at least one executable instruction is stored. When the executable instruction is executed on an electronic device, the electronic device executes the industrial production data management method disclosed in the first aspect and its further embodiments.

[0045] Beneficial effect: The present invention performs redundant processing on industrial production data to obtain initial industrial production data, and then uses a preset association rule algorithm to perform data integration to obtain refined production data, which not only significantly improves the management efficiency of industrial data, but also reduces the complexity of operations in the data access stage, and greatly improves the access convenience of data in the utilization stage. Then, by determining the intelligent early warning indicators of industrial production data, multi-source information extraction is performed on the precise production data, and early warning management of industrial production data is achieved based on multi-source information, providing an efficient and real data basis for production data early warning, realizing intelligent early warning of production data based on big data, improving the efficiency of intelligent early warning, and ensuring safe production. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Flow chart of the industrial production data management method in an embodiment of the present invention.

[0047] Figure 2 Schematic diagram of the structure of an industrial production data management system in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features known in the art are not described.

[0049] The present embodiment discloses a smart industrial production data management method based on big data, including: acquiring industrial production data, and performing redundant processing on the industrial production data to obtain initial industrial production data; using a preset association rule algorithm to perform data integration on the initial industrial production data to obtain precise production data; determining intelligent early warning indicators for the industrial production data; extracting multi-source information from the precise production data, and performing early warning management on the industrial production data based on the multi-source information. The present invention fully considers the multi-source characteristics of the output data information in the actual industrial production process, combines its own independence and distribution, integrates and processes the data, and performs intelligent early warning based on the processed data, providing an efficient and real data basis for production data early warning, realizing intelligent early warning of production data based on big data, improving the efficiency of intelligent early warning, and ensuring safe production. See its flow chart. Figure 1 , the specific steps are:

[0050] S1. Acquire industrial production data, and perform redundancy processing on the industrial production data to obtain initial industrial production data;

[0051] Step S1 specifically includes:

[0052] S11. Obtain industrial production data;

[0053] In order to ensure the reliability of subsequent industrial production data integration, the collected real-time data of the industrial production workshop is processed redundantly, mainly to clear the invalid data in the data collection, so as to minimize the granularity of the data collection and transmission stage without affecting the real mapping of the industrial production data. In the specific execution process, the processing of invalid redundant information is implemented based on the correlation fusion of data. Among them, in the industrial production workshop, the physical workshop RFID and environmental sensors present the data of various types of equipment in the form of data streams, which can be expressed as:

[0054] E r (t)=<T,a(t)>

[0055] E s (t)=<S,R(t),D(t)>

[0056] E e (t)=<E,Q(t),W(t)>

[0057] In the formula, E r (t) is the data information in the physical workshop RFID; E s (t) is the data information collected by the environmental sensor; E e (t) is the operating status data information of the production equipment; T is the unique coding information of the RFID tag; a(t) is the number information of the RFID reader and antenna; S is the number information of the environmental sensor; R(t) is the sensing range parameter of the environmental sensor; D(t) is the data information collected by the environmental sensor; E is the equipment number information of the industrial production workshop; Q(t) is the area information of the industrial production workshop equipment; W(t) is the data set parameter of the equipment status of the production workshop; t is the time parameter corresponding to reading the production workshop data;

[0058] S12. By defining the state information, the data in the above formula is described uniformly with the position information, which is expressed as:

[0059] E(t)=<i,loc,∑W(t)>

[0060] Among them, E(t) is the industrial production data after unified description; i is the coding information; loc is the location information. In this way, for any data acquisition device, in any time period, the original data formed is in the above formula. According to the above formula, the state information of the industrial production data can be obtained to determine whether the industrial production data has changed in the future, and further redundancy processing can be performed.

[0061] S13. When the data status does not change, only the data at the start and end times have integration value. Based on this, the invalid data in the time period where the data status does not change is processed. Specifically, it includes:

[0062] S131. Input the industrial production data after unified description, and query the status information according to the code; the industrial production data obtained according to the above formula contains the status information of the data, so the status information can be queried.

[0063] S132, when the state information is consistent, remove the data information; when the state information is inconsistent, return to continue to query the state information according to the code. In this way, the state information can be screened to achieve redundancy processing.

[0064] According to the above method, the current production status is searched according to the data encoding information, and by comparing the corresponding status parameters at different times, it is determined whether it is redundant data, and data preprocessing is achieved, providing a reliable basis for subsequent data integration.

[0065] S2. Using a preset association rule algorithm to integrate the initial industrial production data to obtain accurate production data;

[0066] Based on the spatial scale and unit level, the characteristics of workshop production tasks are extracted, and the elements in the workshop are combined to describe the state of the entire physical workshop in a dynamic form. The relationship between production service nodes is described, and the logical relationship of the physical workshop is described in real time according to production tasks and plans. At this time, the most direct impact of dynamic adjustment of production tasks is that the physical workshop will also change its state accordingly. In addition, data integration is performed according to the spatial scale association rules. Multiple production service nodes composed of spatial objects and the activities between production service nodes constitute the final physical workshop.

[0067] Step S2 specifically includes:

[0068] S21. According to the initial industrial production data, the production service nodes are refined and divided into flow production service nodes, station production service nodes and cache production service nodes. The relationship between the entire workshop data is expressed as:

[0069] E p (t) = S E +Z E +E E

[0070] Among them, E p (t) is the status data information of the overall physical workshop; S E Provides status data information of mobile production service nodes; Z E Status data information of the workstation production service node; E E To cache the status data information of the production service nodes; the dynamic characteristics of the production service nodes themselves determine that in the physical workshop status data information, the spatial relationship of each production service node also exists in a relatively changing form.

[0071] S22. Use manufacturing tasks to describe the logical relationship between production service nodes. The production data is composed of:

[0072] E p (t) = ∑S Ei +∑Z Ei +∑E Ei

[0073] Among them, ∑S Ei ,∑Z Ei ,∑E EiThey represent the production data with production task i as the core. After integration through workshop association rules, the data can not only reflect the real situation of the workshop structure, but also accurately describe the task logic. After integrating the production data through the above formula, accurate production data is obtained.

[0074] S3. Determine the intelligent early warning index of the industrial production data; wherein the intelligent early warning index is within the safe value range;

[0075] Step S3 specifically includes:

[0076] S31. Determine the standard production data intelligent early warning indicators and the safety value range of a single indicator, and construct an early warning comparison data table based on them;

[0077] S32. Compare the calculation results of the production data intelligent early warning indicator change monitoring with the safety value range in the table to determine whether the specific value of the production data intelligent early warning indicator is within the safety value range. That is, after obtaining a data, the data is put into the early warning comparison data table for search, thereby determining whether the data value is within the safety range, so as to determine whether the production situation corresponding to the data is safe.

[0078] S4. Extract multi-source information from the precise production data, and perform early warning management on the industrial production data based on the multi-source information.

[0079] Step S4 specifically includes:

[0080] S41. Under the premise of ensuring that the intelligent early warning indicators of production data are within the safe value range, extract multi-source information of production data, and use the Apache Spark hybrid framework in big data to obtain the peak value of production data when the node displacement is continuous. Based on cloud computing in big data, correct the errors in the intelligent analysis process of production data. Compared with traditional analysis methods, cloud computing based on big data iteratively solves the peak correction coefficient to extract multi-source information of production data. Let the objective function of this process be:

[0081]

[0082] Among them, r is the production data set; V is the production data index weight allocation vector; x is the production data sub-wavelength; I is the normalized assignment of production data index characteristics; R is the importance between multi-source information of production data; n is the correlation between production data; T is the production data assignment instruction;

[0083] S42. According to the above formula, corresponding numerical points are marked in a two-dimensional coordinate system, wherein the X-axis is used as a multi-source information indicator to extract production data, and the Y-axis is used as a precision indicator based on big data analysis to support the extraction of multi-source information of production data through point positions;

[0084] S43. Analyze the multi-source information of production data according to the production data warning level to obtain the warning result; wherein the production data warning level includes yellow warning, orange warning and red warning, and different colors are used to distinguish different levels of predictions. For different danger level warnings, corresponding specific measures are implemented. That is, the calculated multi-source information of production data is put into the production data warning level for comparison, so as to determine the warning level according to the comparison value, such as red alarm.

[0085] In the design of intelligent early warning methods for production data, a mature database is needed to change and manage multi-source information of production data, and directly update all pre-processed production data to the database. When performing a secondary search, the real-time situation of intelligent early warning of production data can be directly judged through historical records. Finally, according to the comparison results, if the value is within the safe value range, no alarm will be processed. Once it exceeds the safe value range, the alarm device will be triggered immediately, realizing intelligent early warning of production data based on big data.

[0086] In addition, the present invention also provides a smart industrial production data management system based on big data, the structure diagram of which is shown in Figure 2 The industrial production data management system specifically includes:

[0087] An acquisition module 1 is used to acquire industrial production data and perform redundancy processing on the industrial production data to obtain initial industrial production data;

[0088] Integration module 2, used to integrate the initial industrial production data using a preset association rule algorithm to obtain accurate production data;

[0089] Determination module 3, used to determine the intelligent early warning index of the industrial production data; wherein the intelligent early warning index is within the safe value range;

[0090] The extraction module 4 is used to extract multi-source information from the precise production data and perform early warning management on the industrial production data based on the multi-source information.

[0091] In one embodiment, the acquisition module 1 includes:

[0092] The acquisition unit is used to acquire industrial production data. In the industrial production workshop, the physical workshop RFID and environmental sensors present various equipment data in the form of data streams, which can be expressed as:

[0093] E r (t)=<T,a(t)>

[0094] E s(t)=<S,R(t),D(t)>

[0095] E e (t)=<E,Q(t),W(t)>

[0096] In the formula, E r (t) is the data information in the physical workshop RFID; E s (t) is the data information collected by the environmental sensor; E e (t) is the operating status data information of the production equipment; T is the unique coding information of the RFID tag; a(t) is the number information of the RFID reader and antenna; S is the number information of the environmental sensor; R(t) is the sensing range parameter of the environmental sensor; D(t) is the data information collected by the environmental sensor; E is the equipment number information of the industrial production workshop; Q(t) is the area information of the industrial production workshop equipment; W(t) is the data set parameter of the equipment status of the production workshop; t is the time parameter corresponding to reading the production workshop data;

[0097] The description unit is used to describe the data in the above formula in a unified manner using location information, expressed as:

[0098] E(t)=<i,loc,∑W(t)>

[0099] Among them, E(t) is the industrial production data after unified description; i is the coding information; loc is the location information.

[0100] The processing unit is used to process invalid data in the time period when the data state does not change, and only the data at the start time and the end time have integration value.

[0101] In one embodiment, the processing unit includes:

[0102] The query subunit is used to input the industrial production data after unified description and query the status information according to the code;

[0103] The removal subunit is used to remove the data information when the status information is consistent; when the status information is inconsistent, return to continue querying the status information according to the code.

[0104] In one embodiment, the integrated module 2 comprises:

[0105] The refinement unit is used to refine the production service nodes according to the initial industrial production data, and divide them into flow production service nodes, station production service nodes and cache production service nodes. The relationship between the entire workshop data is expressed as:

[0106] E p (t) = S E+Z E +E E

[0107] Among them, E p (t) is the status data information of the overall physical workshop; S E Provides status data information of mobile production service nodes; Z E Status data information of the workstation production service node; E E To cache the status data information of the production service node;

[0108] The integration unit is used to describe the logical relationship between production service nodes using production and manufacturing tasks. The production data is divided into:

[0109] E p (t) = ∑S Ei +∑Z Ei +∑E Ei

[0110] Among them, ∑S Ei ,∑Z Ei ,∑E Ei They respectively represent the production data with production task i as the core.

[0111] In one embodiment, the determination module 3 includes:

[0112] A determination unit is used to determine the standard production data intelligent early warning indicators and the safety value range of a single indicator, and to construct an early warning comparison data table based on this;

[0113] The comparison unit is used to compare the calculation results of the production data intelligent early warning indicator change monitoring with the safety value range in the table to determine whether the specific value of the production data intelligent early warning indicator is within the safety value range.

[0114] In one embodiment, the extraction module 4 comprises:

[0115] The extraction unit is used to extract multi-source information of production data under the premise of ensuring that the intelligent early warning indicators of production data are within the safe value range. The objective function of this process is:

[0116]

[0117] Among them, r is the production data set; V is the production data index weight allocation vector; x is the production data sub-wavelength; I is the normalized assignment of production data index characteristics; R is the importance between multi-source information of production data; n is the correlation between production data; T is the production data assignment instruction;

[0118] A marking unit is used to mark corresponding numerical points in a two-dimensional coordinate system according to the above formula, wherein the X-axis is used as a multi-source information indicator to extract production data, and the Y-axis is used as a precision indicator based on big data analysis to support the extraction of multi-source information of production data through point positions;

[0119] The analysis unit is used to analyze the multi-source information of production data according to the production data warning level to obtain the warning result; wherein the production data warning level includes yellow alarm, orange alarm and red alarm, and different colors are used to distinguish different levels of predictions, and corresponding specific measures are implemented for different danger level warnings.

[0120] The above modules, units and sub-units are used to execute the corresponding steps in the above-mentioned big data-based intelligent production data management method. The specific implementation method thereof is described in the above-mentioned method embodiment and will not be repeated here.

[0121] It should be noted that the above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0122] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0123] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. Although the present invention has been represented and described with reference to specific preferred embodiments, it shall not be interpreted as a limitation of the present invention itself. Various changes can be made to it in form and detail without departing from the spirit and scope of the present invention defined in the attached claims.

Claims

1. An industrial production data management method, characterized in that: The steps include: Acquiring industrial production data, and performing redundancy processing on the industrial production data to obtain initial industrial production data; Using a preset association rule algorithm to integrate the initial industrial production data to obtain accurate production data; Determining the intelligent early warning index of the industrial production data; wherein the intelligent early warning index is within the safe value range; Multi-source information is extracted from the precise production data, and early warning management is performed on the industrial production data based on the extracted multi-source information.

2. The industrial production data management method according to claim 1, characterized in that: The industrial production data includes data information E in the physical workshop RFID r (t), data information E collected by environmental sensors s (t), operating status data information E of production equipment e (t), are expressed as follows: E r (t)=<T,a(t)> E s (t)=<S,R(t),D(t)> E e (t)=<E,Q(t),W(t)> Wherein, T is the unique coding information of the RFID tag; a(t) is the number information of the RFID reader and antenna; S is the number information of the environmental sensor; R(t) is the sensing range parameter of the environmental sensor; D(t) is the data information collected by the environmental sensor; E is the equipment number information of the industrial production workshop; Q(t) is the area information where the equipment in the industrial production workshop is located; W(t) is the data set parameter of the equipment status of the production workshop; and t is the time parameter corresponding to reading the data in the production workshop.

3. The industrial production data management method according to claim 2, characterized in that: Define status information, and convert the data information E in the physical workshop RFID r (t), data information E collected by environmental sensors s (t), operating status data information E of production equipment e (t) is described in a unified way, expressed as: E(t)=<i,loc,∑W(t)> Where E(t) is the industrial production data after unified description; i is the coding information; loc is the location information.

4. The industrial production data management method according to claim 3, characterized in that: The industrial production data is subjected to redundancy processing, specifically comprising: Input the industrial production data E(t) after unified description, and query the status information according to the code; When the status information is consistent, the data information is removed; when the status information is inconsistent, the query of the status information according to the code is returned; this process is repeated to complete the screening of the status information and realize redundancy processing.

5. The industrial production data management method according to claim 1, characterized in that: The initial industrial production data is integrated using a preset association rule algorithm to obtain accurate production data, specifically including: According to the initial industrial production data, the production service nodes are refined and divided into flow production service nodes, workstation production service nodes and cache production service nodes. The relationship between the entire workshop data is expressed as: E p (t)=S E +Z E +E E In the formula, E p (t) is the status data information of the overall physical workshop; S E Provides status data information of mobile production service nodes; Z E Status data information of the workstation production service node; E E To cache the status data information of the production service node; The logical relationship between production service nodes is described using manufacturing tasks, and the production data is divided into: E p (t)=∑S Ei +∑Z Ei +SE Ei In the formula, ∑S Ei ,∑Z Ei ,∑E Ei They respectively represent the flow production data, workstation production data, and cache production data centered on production task i.

6. The industrial production data management method according to claim 1, characterized in that: Determine the intelligent early warning indicators of the industrial production data, specifically including: Determine the standard production data intelligent early warning indicators and the safety value range of a single indicator, and use this to build an early warning comparison data table; Compare the calculation results of the production data intelligent early warning indicator change monitoring with the safety value range in the table to determine whether the specific value of the production data intelligent early warning indicator is within the safety value range.

7. The industrial production data management method according to claim 1, characterized in that: Extracting multi-source information from the precise production data, and performing early warning management on the industrial production data based on the extracted multi-source information, specifically including: The Apache Spark hybrid framework is used to obtain the peak value of production data when the node displacement is continuous; the errors existing in the intelligent analysis process of production data are corrected; the objective function expression of this process is as follows: In the formula, r is the production data set; V is the production data index weight allocation vector; x is the production data sub-wavelength; I is the normalized assignment of production data index features; R is the importance of multi-source information of production data; n is the correlation between production data; T is the production data assignment instruction; According to the objective function expression, the corresponding numerical points are marked in the two-dimensional coordinate system, where the X-axis is used as a multi-source information indicator to extract production data, and the Y-axis is used as a precision indicator based on big data analysis to support the extraction of multi-source information of production data through point positions; Different production data warning levels are divided; the calculated multi-source information of production data is put into the production data warning level for comparison, so as to determine the warning level according to the comparison value.

8. An industrial production data management system, characterized in that: include: An acquisition module, used for acquiring industrial production data and performing redundancy processing on the industrial production data to obtain initial industrial production data; An integration module, used to integrate the initial industrial production data using a preset association rule algorithm to obtain accurate production data; A determination module, used to determine the intelligent early warning index of the industrial production data; wherein the intelligent early warning index is within a safe value range; The extraction module is used to extract multi-source information from the precise production data and perform early warning management on the industrial production data based on the extracted multi-source information.

9. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the industrial production data management method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: At least one executable instruction is stored in the storage medium. When the executable instruction is executed on the electronic device, the electronic device executes the industrial production data management method according to any one of claims 1 to 7.

Images