A factory operation management method and system based on data analysis and processing

Abstract

The present invention discloses a factory operation management method and system based on data analysis and processing, which belongs to the technical field of factory equipment management, and includes: step one, integrating multiple monitoring devices on the factory operation equipment to obtain parameter information of the factory equipment during operation; step two, performing real-time analysis based on the obtained operation parameter information to determine whether the factory equipment is abnormal; step three, performing early warning analysis based on the obtained operation parameter information to determine whether there is a potential abnormal risk of the factory equipment; step four, performing corresponding management of the factory equipment according to the judgment result. The present invention judges the potential risks of the factory equipment by conducting a comprehensive analysis based on the operation status of the factory equipment itself and the operation status of all factory equipment, the real-time operation status of the factory equipment itself and its historical operation status, so that the potential risk status of each factory equipment can be accurately analyzed, which is convenient for timely management of the factory equipment.

Description

Technical Field

[0001] The present invention belongs to the technical field of factory equipment management, and in particular relates to a factory operation management method and system based on data analysis and processing. Background Art

[0002] The fully automated factory is built based on comprehensive technologies such as computer technology, network technology, and automation technology. All production, quality inspection, packaging and other links are completed automatically by programs. Its principle is achieved through sensors, computer programs, robots and other technical means. The products on the fully automated production line are all automatically completed from raw materials to finished products without human intervention.

[0003] The existing methods of operating and managing fully automated factory equipment are mostly through manual routine inspections to determine whether the automatic equipment in the factory is abnormal, so as to carry out timely maintenance and treatment to ensure the normal operation of the factory. However, since manual inspection management requires a large amount of human resources, and the inspection results are easily affected by subjectivity, such as the professional knowledge, experience, responsibility and status of the inspectors on the day, the inspection results are not accurate enough, and different inspection managers may come to different conclusions, resulting in inconsistent results. Summary of the invention

[0004] The purpose of the present invention is to provide a plant operation management method and system based on data analysis and processing to solve the problems faced in the above-mentioned background technology.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A plant operation management method based on data analysis and processing, the management method comprising:

[0007] Step 1: Integrate various monitoring devices on the factory operation equipment to obtain the operating parameter information of the factory equipment;

[0008] Step 2: Perform real-time analysis based on the acquired operating parameter information to monitor the factory equipment in real time to determine whether the factory equipment is abnormal;

[0009] Step 3: If there is no abnormality in the equipment, perform early warning analysis based on the acquired operating parameter information to determine whether there is a potential abnormality risk in the factory equipment;

[0010] Step 4: Manage the factory equipment accordingly based on the judgment results.

[0011] Furthermore, the method for determining whether the factory equipment is abnormal in step 2 is:

[0012] Obtain the parameter values ​​of various monitoring items of factory equipment in real time i , so that through the formula Obtain the alarm trigger value R;

[0013] When R>R Z When the factory equipment is abnormal,

[0014] Where n is the total number of items monitored by factory equipment, and i∈[1,n], α i is the preset coefficient of the ith monitoring item, The optimal indicator parameter value preset for the i-th monitoring item of the factory equipment, R Z It is the preset alarm trigger threshold.

[0015] Furthermore, the method for determining whether there is a potential abnormal risk in the factory equipment in step 3 is:

[0016] When there is no abnormality in the factory equipment, the C According to the obtained alarm trigger value, the alarm trigger value of each factory equipment is plotted over time. j (t);

[0017] Through the formula D = τ1*D L +τ2*D P Obtain the risk value D of each factory equipment;

[0018] When D>D Z When the factory equipment is detected, it is judged that there is a potential abnormal risk;

[0019] Among them, D L is the first status value of each factory equipment, D P is the second status value of each factory equipment, τ1 and τ2 are respective preset coefficients, D Z is the preset risk threshold.

[0020] Furthermore, the first status value D L The method to obtain it is:

[0021] By formula The first state value D is obtained L ;

[0022] Among them, t x is the start time of the detection cycle, t y is the end time of the detection cycle, m is the total number of factory equipment, and j∈[1,m].

[0023] Furthermore, the second status value D P The method to obtain it is:

[0024] By formula The second status value D is obtained P ;

[0025] in, The alarm trigger threshold preset for each factory equipment changes over time, max R is the detection period T C Maximum alarm trigger value within R is the detection period T C Minimum alarm trigger value within R th is the preset alarm trigger comparison value, ρ is the detection period T C The number of times the internal alarm trigger value is greater than the average alarm trigger value.

[0026] Furthermore, the method for managing the factory equipment accordingly according to the judgment result in step 4 is:

[0027] When it is determined that factory equipment is abnormal, the power supply is immediately cut off to stop the equipment from running, and the equipment is repaired accordingly;

[0028] When it is determined that factory equipment has potential abnormal risks, the equipment will be marked and managers will be reminded to check it out.

[0029] A plant operation management system based on data analysis and processing, the management system comprising:

[0030] A parameter acquisition module, which is used to obtain parameter information of factory equipment during operation;

[0031] A monitoring and management center, which analyzes and processes the acquired parameter information to determine whether the factory equipment is abnormal and whether there is a potential abnormal risk;

[0032] An execution module, wherein the execution module manages the factory equipment accordingly according to the judgment result;

[0033] An adjustment module is used to distribute the unfinished task volume of the abnormal factory equipment to the factory equipment without abnormality.

[0034] Furthermore, the working method of the adjustment module is:

[0035] Get the data of each factory equipment in a period of time T n The task completion efficiency g and task completion quality q within a period of time are obtained, and the factory equipment is n Average energy consumption ec and startup time t s ;

[0036] So through the formula Obtain the availability factor U of each factory equipment y ;

[0037] According to the availability coefficient of each factory equipment, sort the factory equipment from large to small, and give priority to allocating the unfinished tasks to the factory equipment with the highest ranking;

[0038] Among them, wd is the task surplus of factory equipment, w, μ, and a are respectively the preset conversion coefficients.

[0039] Beneficial effects of the present invention:

[0040] The present invention acquires parameter information related to the operation of the factory equipment by deploying a variety of detection devices on the factory equipment, and judges the real-time abnormalities and potential risks of the factory equipment according to the parameter information. It does not require manual inspections and can continuously detect the equipment, which can save labor costs and improve the accuracy of detection. At the same time, the various relevant parameter information of the factory equipment is integrated and comprehensively processed, which can eliminate the influence of some accidental errors on the detection results.

[0041] The present invention can also, when the equipment is operating normally, obtain a first status value by analyzing the operating conditions of the factory equipment itself and the operating conditions of all factory equipment, and obtain a second status value by analyzing the real-time operating conditions of the factory equipment itself and its historical operating conditions, and then judge the potential risks of each factory equipment based on the first status value and the second status value. In this way, the potential risk situation of each factory equipment can be accurately analyzed, thereby facilitating timely management of factory equipment, reducing the occurrence of abnormalities in factory equipment, and ensuring normal operation of the factory.

[0042] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 is a flow chart of the method of the present invention;

[0045] Figure 2 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In one embodiment, a method for managing plant operation based on data analysis and processing is disclosed, such as Figure 1 As shown, the management method includes:

[0048] Step 1: Integrate various monitoring devices on the factory operation equipment to obtain the operating parameter information of the factory equipment;

[0049] Step 2: Perform real-time analysis based on the acquired operating parameter information to monitor the factory equipment in real time to determine whether the factory equipment is abnormal;

[0050] Step 3: If there is no abnormality in the equipment, perform early warning analysis based on the acquired operating parameter information to determine whether there is a potential abnormality risk in the factory equipment;

[0051] Step 4: Manage the factory equipment accordingly based on the judgment results.

[0052] Through the above technical scheme, the present application obtains parameter information related to the operation of factory equipment by deploying multiple detection devices on factory equipment, and judges the real-time abnormalities and potential risks of factory equipment according to the parameter information. It does not require manual inspections and can continuously detect equipment to improve the accuracy of detection; at the same time, the various relevant parameter information of factory equipment is integrated and comprehensively processed, thereby eliminating the influence of some accidental errors on the detection results; in addition, the present application can also obtain a first status value based on the operation status of the factory equipment itself and the operation status of all factory equipment under normal equipment operation, and obtain a second status value based on the real-time operation status of the factory equipment itself and its historical operation status, and then judge the potential risks of each factory equipment according to the first status value and the second status value. In this way, the potential risk status of each factory equipment can be accurately analyzed, thereby facilitating timely management of factory equipment to reduce the occurrence of abnormalities in factory equipment and ensure normal operation of the factory.

[0053] The method for judging whether the factory equipment is abnormal in step 2 is: obtaining the parameter values ​​of various monitoring items of the factory equipment in real time pt i , so that through the formula Obtain the alarm trigger value R;

[0054] When R>RZ When the factory equipment is abnormal,

[0055] Where n is the total number of items monitored by factory equipment, and i∈[1,n], α i is the preset coefficient of the ith monitoring item, The optimal indicator parameter value preset for the i-th monitoring item of the factory equipment, R Z It is the preset alarm trigger threshold.

[0056] The above technical solution discloses a specific method for determining whether factory equipment is abnormal in real time. First, the parameter values ​​of various monitoring items of factory equipment are obtained. i , such as operating temperature or current value during operation, and then through the formula The alarm trigger value R is obtained. Since each monitoring item has the most suitable parameter, the obtained parameter value is compared with the preset optimal index parameter value. Obviously, when the value is larger, it is more likely that the factory equipment is abnormal. Since some project parameters have a mutual influence relationship, for example, when the equipment current is abnormal, its temperature will also rise. Therefore, in order to avoid the influence of accidental errors on the detection results, this embodiment comprehensively analyzes all monitored project parameters to obtain an alarm trigger value, and then compares the obtained alarm trigger value R with the preset alarm trigger threshold R. Z For comparison, when R>R Z In this way, various parameter information of factory equipment can be integrated and processed, thus eliminating the influence of some accidental errors on the detection results and increasing the accuracy of monitoring.

[0057] It should be noted that the preset coefficient α of each monitoring item i , the optimal indicator parameter values ​​preset for each monitoring project And the preset alarm trigger threshold R Z All of them can be determined based on the historical operating data of the factory equipment combined with empirical data, so they will not be described here.

[0058] The method for determining whether there is a potential abnormal risk in the factory equipment in step 3 is: when there is no abnormality in the factory equipment, every detection period T C According to the obtained alarm trigger value, the alarm trigger value of each factory equipment is plotted over time. j (t);

[0059] Through the formula D = τ1*D L +τ2*D P Obtain the risk value D of each factory equipment;

[0060] When D>DZ When the factory equipment is detected, it is judged that there is a potential abnormal risk;

[0061] Among them, D L is the first status value of each factory equipment, D P is the second status value of each factory equipment, τ1 and τ2 are respective preset coefficients, D Z is the preset risk threshold;

[0062] The first state value D L The method of obtaining is: through the formula Get the first status value D L ;

[0063] Among them, t x is the start time of the detection cycle, t y is the end time of the detection cycle, m is the total number of factory equipment, and j∈[1,m];

[0064] The second state value D P The method of obtaining is: through the formula The second status value D is obtained P ;

[0065] in, The alarm trigger threshold preset for each factory equipment changes over time, max R is the detection period T C Maximum alarm trigger value within R is the detection period T C Minimum alarm trigger value within R th is the preset alarm trigger comparison value, ρ is the detection period T C The number of times the internal alarm trigger value is greater than the average alarm trigger value.

[0066] The above technical solution provides a specific method for determining whether there is a potential abnormal risk in factory equipment. First, when there is no abnormality in the factory equipment, the detection period T is set to C According to the obtained alarm trigger value, the alarm trigger value of each factory equipment is plotted over time. j (t), and then first use the formula Get the first status value D L , and then through the formula The second status value D is obtained P , and finally through the formula D = τ1*D L +τ2*D PThe risk value D of each factory equipment is obtained, and the factory equipment has potential abnormal risks according to the size of the risk value D; from the formula It can be seen that the formula Indicates that in the detection period T C The overall difference between a single plant device and all plant devices within the formula It means that at the current end time point t y The overall difference between a single factory equipment and all factory equipment is analyzed by combining historical data and real-time data to judge the operating status of each factory equipment. All factory equipment are in the same area. Obviously, when the first status value D L The larger the value, the greater the possibility of potential abnormal risk in factory equipment. It can be seen that the formula It represents the difference between the cumulative alarm trigger value change of the factory equipment and the preset alarm trigger threshold change. Obviously, the closer the alarm trigger change curve is to the alarm threshold, the greater the possibility of abnormal risk of the equipment. That is, when the formula The larger the value of is, the greater the possibility of abnormal risk of the equipment, and the formula Indicates that in the detection period T C The difference between the maximum alarm trigger value and the minimum alarm trigger value is obviously larger when the value is larger, or the detection period T C The higher the number of times the internal alarm trigger value is greater than the average alarm trigger value, the greater the possibility of abnormal risk of the equipment. P The larger the value, the greater the possibility of potential abnormal risk in factory equipment; so finally, the formula D = τ1*D L +τ2*D P Combined with the first condition value and the second condition value, a comprehensive analysis is performed to obtain the risk value D of each factory equipment, and then compared with the preset risk threshold D Z Compare, when D>D Z When the factory equipment is abnormal, it means that there is an abnormal risk at this time, and the factory equipment is judged to have a potential abnormal risk. In this way, when the factory equipment is operating normally, the first status value can be obtained by analyzing the operating conditions of the factory equipment itself and all the factory equipment, and the second status value can be obtained by analyzing the real-time operating conditions of the factory equipment and its historical operating conditions. The potential risk of each factory equipment can be judged based on the first status value and the second status value. In this way, the potential risk of each factory equipment can be accurately analyzed, so as to facilitate timely management of the factory equipment, reduce the occurrence of abnormal factory equipment, and ensure the normal operation of the factory.

[0067] It should be noted that the preset coefficients τ1 and τ2, the preset risk threshold D Z And the preset alarm trigger comparison value R th All of them can be determined based on the historical operation data of the factory equipment combined with empirical data, and the alarm trigger threshold preset by each factory equipment changes over time. It is determined based on the alarm data of relevant factory equipment in the big data, and the detection cycle T C The duration can be determined artificially based on actual conditions, so I will not go into details here.

[0068] In step 4, the method for managing factory equipment accordingly based on the judgment results is:

[0069] When it is determined that factory equipment is abnormal, the power supply is immediately cut off to stop the equipment from running, and the equipment is repaired accordingly;

[0070] When it is determined that factory equipment has potential abnormal risks, the equipment will be marked and management personnel will be reminded to check it out.

[0071] In the above scheme, when it is determined that factory equipment has an abnormality, in order to ensure the quality of subsequent products and equipment safety, the relevant power supply of the factory equipment is immediately cut off to prevent the equipment from running. At the same time, relevant processing personnel are promptly sent to perform corresponding maintenance on the factory equipment to restore the normal operation of the factory equipment in time; and when it is determined that there is a potential abnormal risk in the factory equipment, the equipment is marked and the management personnel are reminded to go and check it. The specific potential risks are determined by checking the various operating parameters, and they are dealt with in a timely manner to ensure the stable operation of the factory equipment.

[0072] In another embodiment, a plant operation management system based on data analysis and processing is disclosed. The management system is implemented by the plant operation management method based on data analysis and processing described above. Figure 2 As shown, the management system includes:

[0073] Parameter acquisition module, which is used to obtain parameter information of factory equipment during operation;

[0074] The monitoring and management center analyzes and processes the acquired parameter information to determine whether the factory equipment has any abnormalities and whether there are potential abnormal risks;

[0075] An execution module manages the factory equipment accordingly based on the judgment results;

[0076] An adjustment module, the adjustment module is used to allocate the unfinished task amount of the abnormal factory equipment to the factory equipment without abnormality;

[0077] The working method of the adjustment module is to obtain the data of each factory equipment over a period of time T n The task completion efficiency g and task completion quality q within a period of time are obtained, and the factory equipment is n Average energy consumption ec and startup time t s ;

[0078] So through the formula Obtain the availability factor U of each factory equipment y ;

[0079] According to the availability coefficient of each factory equipment, sort the factory equipment from large to small, and give priority to allocating the unfinished tasks to the factory equipment with the highest ranking;

[0080] Among them, wd is the task surplus of factory equipment, w, μ, and a are respectively the preset conversion coefficients.

[0081] Through the above technical solution, the adjustment module set in the present application allocates the unfinished task volume of the abnormal factory equipment to the factory equipment without abnormality, thereby reducing the accumulation of tasks and ensuring the processing efficiency of the entire factory. Specifically, the adjustment module of each factory equipment in a period of time T n The task completion efficiency g and task completion quality q within a period of time are obtained, and the factory equipment is n Average energy consumption ec and startup time t s , so that through the formula Obtain the availability factor U of each factory equipment y ; The preset conversion coefficients w, μ, And a can be determined based on historical experience data. From the formula, it can be seen that when the efficiency of the factory equipment in completing tasks is higher, the quality of the tasks is better, or the average energy consumption is smaller, and the time of operation is shorter, it means that the possibility that the factory equipment can continue to process the tasks is greater. Similarly, if the number of tasks in the factory equipment inventory is smaller, the possibility that it can continue to process the tasks is greater. Therefore, when the availability coefficient U y The larger the value, the greater the possibility that it can continue to process the task volume, and the greater the task volume that can be processed. y According to the size of the factory equipment, the factory equipment is sorted from large to small, and the unfinished tasks are assigned to the top-ranked factory equipment first, and the corresponding assigned tasks are increased accordingly. In this way, the remaining tasks of the stopped factory equipment can be reasonably distributed to the factory equipment in processing, so as to reduce the accumulation of tasks and ensure the processing efficiency of the entire factory.

[0082] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

Claims

1. A factory operation management method based on data analysis and processing, characterized in that: The management method comprises: Step 1: Integrate multiple monitoring devices on the factory operation equipment to obtain the operating parameter information of the factory equipment; Step 2: Perform real-time analysis based on the acquired operating parameter information to monitor the factory equipment in real time to determine whether the factory equipment is abnormal; Step 3: If there is no abnormality in the equipment, perform early warning analysis based on the acquired operating parameter information to determine whether there is a potential abnormal risk in the factory equipment; Step 4: Manage the factory equipment accordingly based on the judgment results.

2. A factory operation management method based on data analysis and processing according to claim 1, characterized in that: The method for determining whether the factory equipment is abnormal in step 2 is: Obtain the parameter values ​​of various monitoring items of factory equipment in real time i , so that through the formula Obtain the alarm trigger value R; When R>R Z When the factory equipment is abnormal, Where n is the total number of items monitored by factory equipment, and i∈[1,n], α i is the preset coefficient of the ith monitoring item, The optimal indicator parameter value preset for the i-th monitoring item of the factory equipment, R Z It is the preset alarm trigger threshold.

3. A factory operation management method based on data analysis and processing according to claim 2, characterized in that: The method for determining whether there is a potential abnormal risk in the factory equipment in step 3 is: When there is no abnormality in the factory equipment, the C According to the obtained alarm trigger value, the alarm trigger value of each factory equipment is plotted over time. j (t); By the formula D = T1 * D L +T2*D P Obtain the risk value D of each factory equipment; When D>D Z When the factory equipment is detected, it is judged that there is a potential abnormal risk; Among them, D L is the first status value of each factory equipment, D P is the second status value of each factory equipment, τ1 and T2 are respective preset coefficients, D Z is the preset risk threshold.

4. A factory operation management method based on data analysis and processing according to claim 3, characterized in that: The first status value D L The method to obtain it is: By formula The first state value D is obtained L ; Among them, t x is the start time of the detection cycle, t y is the end time of the detection cycle, m is the total number of factory equipment, and j∈[1,m].

5. A factory operation management method based on data analysis and processing according to claim 3, characterized in that: The second status value D P The method to obtain it is: By formula The second status value D is obtained P ; in, The alarm trigger threshold preset for each factory equipment changes over time, max R is the detection period T C Maximum alarm trigger value within R is the detection period T C Minimum alarm trigger value within R th is the preset alarm trigger comparison value, ρ is the detection period T C The number of times the internal alarm trigger value is greater than the average alarm trigger value.

6. A factory operation management method based on data analysis and processing according to claim 1, characterized in that: The method for managing the factory equipment accordingly according to the judgment result in step 4 is: When it is determined that factory equipment is abnormal, the power supply is immediately cut off to stop the equipment from running, and the equipment is repaired accordingly; When it is determined that factory equipment has potential abnormal risks, the equipment will be marked and managers will be reminded to check it out.

7. A plant operation management system based on data analysis and processing, the system being implemented by the plant operation management method based on data analysis and processing according to any one of claims 1 to 6, characterized in that: The management system comprises: A parameter acquisition module, which is used to obtain parameter information of factory equipment during operation; A monitoring and management center, which analyzes and processes the acquired parameter information to determine whether the factory equipment is abnormal and whether there is a potential abnormal risk; An execution module, wherein the execution module manages the factory equipment accordingly according to the judgment result; An adjustment module is used to distribute the unfinished task volume of the abnormal factory equipment to the factory equipment without abnormality.

8. A plant operation management system based on data analysis and processing according to claim 7, characterized in that: The working method of the adjustment module is: Get the data of each factory equipment in a period of time T n The task completion efficiency g and task completion quality q within a period of time are obtained, and the factory equipment is n Average energy consumption ec and startup time t s ; So through the formula Obtain the availability factor U of each factory equipment y ; According to the availability coefficient of each factory equipment, sort the factory equipment from large to small, and give priority to allocating the unfinished tasks to the factory equipment with the highest ranking; Among them, wd is the task surplus of factory equipment, w, μ, and a are respectively the preset conversion coefficients.

Images