CN117077993B - Workshop material automatic weighing data management system and method based on artificial intelligence - Google Patents
Workshop material automatic weighing data management system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN117077993B CN117077993B CN202311347942.2A CN202311347942A CN117077993B CN 117077993 B CN117077993 B CN 117077993B CN 202311347942 A CN202311347942 A CN 202311347942A CN 117077993 B CN117077993 B CN 117077993B
- Authority
- CN
- China
- Prior art keywords
- weighing
- data
- batch
- measured
- processing flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005303 weighing Methods 0.000 title claims abstract description 610
- 239000000463 material Substances 0.000 title claims abstract description 237
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000013523 data management Methods 0.000 title claims abstract description 22
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 43
- 238000012544 monitoring process Methods 0.000 claims description 60
- 230000002159 abnormal effect Effects 0.000 claims description 58
- 239000012634 fragment Substances 0.000 claims description 39
- 238000001514 detection method Methods 0.000 claims description 24
- 230000035772 mutation Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000012098 association analyses Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000003247 decreasing effect Effects 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 7
- 101100007538 Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987) cpc-1 gene Proteins 0.000 claims description 6
- 101100067991 Schizosaccharomyces pombe (strain 972 / ATCC 24843) rkp1 gene Proteins 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000007726 management method Methods 0.000 claims description 4
- 101100108853 Mus musculus Anp32e gene Proteins 0.000 claims description 3
- 101100221809 Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987) cpd-7 gene Proteins 0.000 claims description 3
- 101150025236 dmaW gene Proteins 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 abstract description 3
- 230000005856 abnormality Effects 0.000 abstract description 2
- 239000002245 particle Substances 0.000 description 27
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the technical field of weighing data management, in particular to an automatic workshop material weighing data management system and method based on artificial intelligence. According to the invention, the problem of weighing data abnormality caused by deviation of weighing precision of the weighing apparatus along with the use time and the accumulation of the weighing data under the condition that the weighing apparatus cannot perform the zeroing calibration operation in time in the dynamic weighing process is considered; and the weighing machine is linked with information or equipment such as a plan, materials and the like, so that the regulation and control of the weighing machine return-to-zero calibration operation and the control of the dynamic weighing data precision are realized, and the unmanned realization of workshop procedure weighing is ensured.
Description
Technical Field
The invention relates to the technical field of weighing data management, in particular to an automatic workshop material weighing data management system and method based on artificial intelligence.
Background
In the metallurgical industry, the weighing modes of material circulation among working procedures generally comprise a hanging hook scale, a crown block scale, a platform scale and the like, if static weighing is adopted, the materials are kept still, and the weight is obtained after the instrument data are stable, although the accuracy is higher, the efficiency is lower, so that a dynamic weighing system is researched to improve the weighing efficiency. In the dynamic weighing process, the high-precision actual weight is difficult to obtain due to the influence of interference factors such as vibration, impact, speed and the like.
Meanwhile, in the process of dynamic weighing, as the weighing equipment is always running, the weighing apparatus cannot perform zero setting operation in time, and in the process of using the weighing apparatus, along with the use time and the accumulation of weighing data, the weighing precision of the weighing apparatus can gradually deviate, so that the problem of abnormal weighing data can occur; therefore, how to adjust the time of the weighing apparatus to execute the zeroing operation can intuitively reflect the precision of weighing data to a certain extent, in the prior art, the zeroing operation is often executed on the weighing apparatus by setting a fixed time length, and the method has the great defect that on one hand, the weighing efficiency (total weighing time length) of the weighing apparatus cannot be effectively reduced, and on the other hand, the weighing apparatus cannot be linked with information or equipment such as a plan, materials and the like, so that the unmanned weighing of workshop procedures is truly realized.
Disclosure of Invention
The invention aims to provide an automatic workshop material weighing data management system and method based on artificial intelligence, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the automatic weighing data management method for workshop materials based on artificial intelligence comprises the following steps:
s1, acquiring the number of a batch of a material to be measured and the processing flow of the current time, and acquiring the time period from the entering of the material to be measured to the exiting of the weighing apparatus, wherein the time period is recorded as a dynamic weighing interval; acquiring monitoring information of a built-in sensor of the weighing apparatus in a dynamic weighing interval in a dynamic material weighing process in real time through the built-in sensor of the weighing apparatus, wherein the monitoring information comprises detection data respectively corresponding to different times of the vibration sensor and the weighing sensor in the dynamic weighing process;
s2, dividing the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data, and judging the relevance among the data fragments divided by different sensor monitoring information; analyzing abnormal deviation of weighing states among the associated data segments, and predicting weighing values of the weighing materials in the batch of the materials to be measured by combining the associated data segments with the minimum abnormal deviation values of the weighing states to obtain weighing values corresponding to the batch of the materials to be measured in the current processing flow;
S3, inquiring a weighing result corresponding to the number of the batch of the material to be measured in the previous processing flow in a historical weighing database, marking the weighing result as reference weighing information, acquiring execution state information of the weighing instrument when the reference weighing information is acquired in the database, combining the execution state information of the weighing instrument when the weighing value corresponding to the current processing flow of the batch of the material to be measured is acquired, and predicting the theoretical weighing deviation amount of the instrument existing in the weighing value corresponding to the current processing flow of the batch of the material to be measured;
s4, according to a theoretical weighing value corresponding to the current processing flow of the material batch to be measured and an appliance theoretical weighing deviation value existing in the corresponding weighing value, obtaining a theoretical weighing fluctuation interval corresponding to the current processing flow of the material batch to be measured; the theoretical weighing value of the batch of the material to be measured corresponding to the current processing flow is obtained by inquiring a database preset form;
s5, judging whether the weighing value of the material batch to be measured corresponding to the current processing flow is abnormal or not according to the weighing value of the material batch to be measured corresponding to the current processing flow and the corresponding theoretical weighing fluctuation interval, stopping continuously weighing the material in an abnormal state, carrying out zero resetting calibration on the weighing instrument, and dynamically weighing the weight of the material batch to be measured corresponding to the current processing flow again before inserting the material batch to be measured in the abnormal state into other non-weighed material batches; the number of the weighed material batches executed in the time interval of executing zero calibration on the weighing apparatus in two adjacent times is larger than n, and n is more than or equal to 1;
S6, managing weighing results of the material batches in different processing flows, and feeding back the material batches corresponding to the abnormal weighing results to an administrator.
Further, in the step S1, the dynamic weighing interval is marked as [ T1, T2]; recording detection data corresponding to time T of a vibration sensor in monitoring information of a built-in sensor of the weighing apparatus as Zt, wherein T is E [ T1, T2]; the detection data corresponding to the time t of the weighing sensor in the monitoring information of the built-in sensor of the weighing apparatus is recorded as Ct;
the method for dividing the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process in the S2 comprises the following steps:
s201, acquiring vibration sensor monitoring data corresponding to different time points in sensor monitoring information in a dynamic weighing interval in a dynamic weighing process, and constructing a monitoring data pair by each monitoring data and the corresponding time point, wherein tz is one time point in the dynamic weighing interval, and Atz represents the data monitored by the vibration sensor at the time point tz in the dynamic weighing process;
s202, marking coordinate points corresponding to the monitoring data obtained in the S201 in a first plane rectangular coordinate system, and connecting adjacent marking points in the first plane rectangular coordinate system to obtain a vibration amplitude line graph, wherein the first plane rectangular coordinate system is constructed by taking time as an x axis and vibration amplitude monitored by a vibration sensor as a y axis;
S203, marking each relation mutation node in the vibration amplitude line graph, wherein the relation mutation node is a turning point of converting the data in the vibration amplitude line graph from an increasing relation to a decreasing relation or from the decreasing relation to the increasing relation, the time corresponding to the relation mutation node is taken as a cutting position, the vibration amplitude line graph is divided into a plurality of data fragments, and the number of the divided data fragments is equal to the number of the corresponding relation mutation nodes plus one;
the relation mutation node is a point corresponding to each maximum value and each minimum value in the corresponding function of the corresponding line graph, the relation mutation node can only feed back the change trend of the corresponding function of the corresponding line graph in each part, the point corresponding to the maximum value represents the turning point of the data in the corresponding line graph from the increasing relation to the decreasing relation, the point corresponding to the minimum value represents the turning point of the data in the corresponding line graph from the decreasing relation to the increasing relation, no clear numerical value relation exists between the maximum value and the minimum value, and the maximum value is possibly more than or equal to the minimum value;
s204, constructing a second plane rectangular coordinate system, and constructing a weighing data line graph according to the method in S201-S202, wherein the second plane rectangular coordinate system is constructed by taking time as a horizontal axis and monitoring data of a weighing sensor as a vertical axis; taking the time corresponding to the relation mutation node obtained in the step S203 as a cutting position, and dividing the weighing data line graph into a plurality of data fragments;
The method for judging the relevance between the data segments divided by the monitoring information of the different sensors in the S2 comprises the following steps:
s211, acquiring data fragments corresponding to the vibration amplitude line graph in S203 and data fragments corresponding to the weighing data line graph in S204, wherein each data fragment corresponds to a time interval, binding two data fragments with the same corresponding time interval in the data fragments corresponding to the vibration amplitude line graph and the weighing data line graph, and each binding result corresponds to the data fragment corresponding to one weighing data line graph and the data fragment corresponding to one vibration amplitude line graph respectively; the data segment corresponding to the weighing data line graph corresponding to the ith binding result is marked as FCi, and the data segment corresponding to the vibration amplitude line graph corresponding to the ith binding result is marked as FZi;
s212, acquiring a binding association value between FCi and FZi in the ith binding result, which is marked as Gi,
the gi=1/(i 2-i 1) ·ζ b=i1 b=i2 |FCi（b）-H[FZi（b）]|db，
Wherein i1 represents the minimum value of the corresponding time interval of the data segment in the ith binding result, i2 represents the maximum value of the corresponding time interval of the data segment in the ith binding result, FCi (b) represents the corresponding weighing data in FCi when the time is b, FZi (b) represents the corresponding vibration amplitude in FZi when the time is b, H [ FZi (b) ] represents the function value after conversion of FZi (b),
H[FZi(b)]=[FCi(i2)-FCi(i1)]/[FZi(i2)-FZi(i1)]·{FZi(b)-FZi(i1)}+FCi(i1)，
Wherein FCi (i 2) represents the corresponding weighing data in time i2 and FCi, FCi (i 1) represents the corresponding weighing data in time i1 and FCi, FZi (i 2) represents the corresponding vibration amplitude in time i2 and FZi, and FZi (i 1) represents the corresponding vibration amplitude in time i1 and FZi; default FZi (i 2) is not equal to FZi (i 1);
in the invention, because the data segments FCi and FZi belong to different variable relations respectively, the data segments FCi and FZi cannot be directly compared and operated, the data segments can be operated only by converting the data segments into the same dimension, the conversion function corresponding to H </u > ] is used for converting FZi, and H </u > [ FZi (b) ] is used for converting a value interval corresponding to FZi when b is different in value into a value interval corresponding to FCi, and further analyzing a binding association value (deviation condition) between the data segments; the binding association value between FCi and FZi in the binding result is obtained to obtain the difference condition of FCi and FZi on the function graph structure;
s213, comparing Gi with a binding association threshold, wherein the binding association threshold is a preset constant in a database,
when Gi is greater than or equal to the binding association threshold, judging that the association relation between FCi and FZi in the ith binding result does not exist, and the sensor monitoring data in the bound data fragment is interfered by noise;
When Gi is smaller than the binding association threshold, it is determined that the association relationship exists between FCi and FZi in the ith binding result.
Further, the method for predicting the weighing value of the weighing material in the batch of the material to be measured in S2 includes the following steps:
s221, acquiring a binding result with an association relationship, numbering the acquired binding result, and predicting a weighing result corresponding to the vibration amplitude of 0 according to a data segment in the kth binding result with the association relationship, and marking as CYk;
when the vibration amplitude is 0 in the data segment belonging to the vibration amplitude line diagram in the kth binding result with the association relation, acquiring a time point with the vibration amplitude of 0, and marking the time point as tsk, wherein CYk is equal to the weighing result when the time in the data segment belonging to the weighing data line diagram in the kth binding result with the association relation is tsk;
when the condition that the vibration amplitude is 0 does not exist in the data segment belonging to the vibration amplitude line graph in the kth binding result with the association relation, acquiring the corresponding time point when the amplitude is 0 on the straight line corresponding to the two endpoints in the data segment belonging to the vibration amplitude line graph, and recording the time point as tLk, wherein CYk is equal to the weighing result when the time is tsk on the straight line corresponding to the two endpoints in the data segment belonging to the weighing data line graph in the kth binding result with the association relation;
The range of vibration amplitude corresponding to the vibration sensor is positive number, 0 and negative number;
s222, obtaining a weighing value corresponding to the current processing flow of the batch of the material to be measured, wherein the weighing value corresponding to the current processing flow of the batch of the material to be measured is equal to the average value of the predicted values of the weighing results when the vibration amplitudes corresponding to the binding results with the association relations are 0.
Further, in the step S3, in the process of obtaining the execution state information of the weighing apparatus, the starting time tq of weighing the batch of the material to be measured in the corresponding processing flow by the weighing apparatus and the time tg of the last execution of the zeroing calibration operation by the corresponding weighing apparatus are obtained; recording weighing data corresponding to time tm of the weighing apparatus in a time period from tg to tq as Ctm, and enabling corresponding execution state information of the weighing apparatus to be ≡ tm=tg tm=tq Ctmdtm, tm e [ tg, tq]And tg is less than or equal to tq;
the method for predicting the theoretical weighing deviation amount of the instrument, which exists in the weighing value corresponding to the current processing flow, of the batch of the material to be detected in the S3 comprises the following steps:
s311, obtaining deviation weighing intervals corresponding to different execution state information of the weighing apparatus in the database pre-manufactured form, marking the deviation weighing intervals corresponding to the execution state information of the weighing apparatus corresponding to the reference weighing information as [ Cpc1, cpc2], marking the deviation weighing intervals corresponding to the execution state information of the weighing apparatus corresponding to the current processing flow of the batch of materials to be tested as [ Cpd1, cpd2],
Wherein Cpc1 represents the minimum value of the corresponding weighing deviation amount when the execution state information of the weighing apparatus in the database is the execution state information of the weighing apparatus corresponding to the reference weighing information (when the execution state information of the weighing apparatus reaches the execution state information of the weighing apparatus corresponding to the reference weighing information through detecting, under the condition of stopping continuous weighing, the difference value between the indication number and 0 on the weighing apparatus obtains the corresponding weighing deviation amount); cpc2 represents that the execution state information of the weighing instrument in the database is the maximum value of the corresponding weighing deviation amount when the weighing instrument is corresponding to the execution state information of the weighing instrument by referring to the weighing information; cpd1 represents the minimum value of the corresponding weighing deviation amount when the execution state information of the weighing instrument in the database is the execution state information of the weighing instrument corresponding to the current processing flow of the material batch to be measured; cpd2 represents the maximum value of corresponding weighing deviation amount when the execution state information of the weighing instrument in the database is the execution state information of the weighing instrument corresponding to the current processing flow of the material batch to be measured;
s312, obtaining a predicted value of the theoretical weighing deviation of the instrument existing in the weighing value corresponding to the current processing flow of the batch of the material to be measured, and recording the predicted value as [ min { Cpd1-Cpc1, cpd2-Cpc2}, max { Cpd1-Cpc1, cpd2-Cpc2} ],
Where min { Cpd1-Cpc1, cpd2-Cpc2} represents the minimum of Cpd1-Cpc1 and Cpd2-Cpc2 and max { Cpd1-Cpc1, cpd2-Cpc2} represents the maximum of Cpd1-Cpc1 and Cpd2-Cpc 2.
Further, in the step S4, the theoretical weighing fluctuation interval of the batch of the material to be measured corresponding to the current processing flow is recorded as [ d1+d2, d1+d3], wherein D1 represents the theoretical weighing value of the batch of the material to be measured corresponding to the current processing flow, D2 represents the minimum value of the theoretical weighing deviation amount of the batch of the material to be measured in the appliance existing in the weighing value corresponding to the current processing flow, and D3 represents the maximum value of the theoretical weighing deviation amount of the batch of the material to be measured in the appliance existing in the weighing value corresponding to the current processing flow;
s5, judging whether the weighing value of the batch of the material to be measured corresponding to the current processing flow is abnormal, acquiring the weighing value of the batch of the material to be measured corresponding to the current processing flow and a corresponding theoretical weighing fluctuation interval,
when the weighing value corresponding to the material batch to be measured in the current processing flow belongs to the corresponding theoretical weighing fluctuation interval, judging that the weighing value corresponding to the material batch to be measured in the current processing flow is normal;
when the weighing value corresponding to the material batch to be measured in the current processing flow does not belong to the corresponding theoretical weighing fluctuation interval, judging that the weighing value corresponding to the material batch to be measured in the current processing flow is abnormal.
The invention judges whether the weighing value of the batch of materials to be measured corresponding to the current processing flow is abnormal or not, and aims to obtain the judging condition for executing the zeroing calibration operation on the weighing apparatus, thereby realizing the control of the weighing precision of the weighing apparatus in the dynamic weighing process.
The invention is characterized in that the artificial intelligence is combined with the weighing condition of the weighing apparatus, the prediction of the weighing value of the batch of the material to be measured corresponding to the current processing flow and the prediction analysis of the corresponding theoretical weighing fluctuation interval are realized, and the intelligent management and control of the weighing apparatus zeroing calibration operation are realized by combining the comparison result of the two, so that the weighing is unmanned to a certain extent.
Further, when the weighing results of the material batches in different processing flows are managed in S6, if the same material batch is continuously weighed twice in the same processing flow, the state of the weighing result of the second time is used as the state of the corresponding material batch to which the weighing value corresponding to the corresponding processing flow belongs.
Workshop material automatic weighing data management system based on artificial intelligence, the system includes following modules:
the weighing data dynamic acquisition module acquires the serial number of the batch of the material to be measured and the processing flow of the current time, and acquires the time period from the entering of the material to be measured to the exiting of the weighing apparatus, and the time period is recorded as a dynamic weighing interval; acquiring monitoring information of a sensor arranged in the weighing apparatus in a dynamic weighing interval in a material dynamic weighing process in real time through the sensor arranged in the weighing apparatus;
The detection information segmentation and association analysis module is used for segmenting the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data and judging the association between the data segments after different sensor monitoring information segmentation; analyzing abnormal deviation of weighing states among the associated data segments, and predicting weighing values of the weighing materials in the batch of the materials to be measured by combining the associated data segments with the minimum abnormal deviation values of the weighing states to obtain weighing values corresponding to the batch of the materials to be measured in the current processing flow;
the theoretical weighing deviation prediction module is used for inquiring a weighing result corresponding to the previous processing flow of the batch number of the material to be measured in the historical weighing database, marking the weighing result as reference weighing information, acquiring the execution state information of the weighing instrument when the reference weighing information is acquired in the database, combining the execution state information of the weighing instrument when the weighing value corresponding to the current processing flow of the material batch to be measured is acquired, and predicting the theoretical weighing deviation of the instrument existing in the weighing value corresponding to the current processing flow of the material batch to be measured;
the weighing fluctuation analysis module obtains a theoretical weighing fluctuation interval corresponding to the material batch to be measured in the current processing flow according to a theoretical weighing value corresponding to the material batch to be measured in the current processing flow and an appliance theoretical weighing deviation value existing in the corresponding weighing value;
The zeroing calibration operation management module judges whether the weighing value of the material batch to be measured corresponding to the current processing flow is abnormal or not according to the weighing value of the material batch to be measured corresponding to the current processing flow and the corresponding theoretical weighing fluctuation interval, stops continuously weighing the material in an abnormal state, performs zeroing calibration on the weighing apparatus, and dynamically weighs the material batch to be measured again corresponding to the current processing flow before inserting the material batch to be measured in the abnormal state into other non-weighed material batches;
the abnormal feedback module is used for managing weighing results of the material batches in different processing flows and feeding back the material batches corresponding to the abnormal weighing results to an administrator.
Furthermore, the detection information segmentation and association analysis module comprises a data segment segmentation unit, an association analysis unit and a weighing prediction unit,
the data segment dividing unit divides the segments of the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data;
the relevance analysis unit judges relevance among the data fragments divided by the monitoring information of different sensors;
The weighing prediction unit analyzes the abnormal deviation of the weighing state between the associated data segments, predicts the weighing value of the weighing material in the batch of the material to be measured by combining the associated data segment with the minimum abnormal deviation value of the weighing state, and obtains the weighing value of the batch of the material to be measured corresponding to the current processing flow.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, the problem of weighing data abnormality caused by deviation of weighing precision of the weighing apparatus along with the use time and the accumulation of the weighing data under the condition that the weighing apparatus cannot perform the zeroing calibration operation in time in the dynamic weighing process is considered; and the weighing machine is linked with information or equipment such as a plan, materials and the like, so that the regulation and control of the weighing machine return-to-zero calibration operation and the control of the dynamic weighing data precision are realized, and the unmanned realization of workshop procedure weighing is ensured.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a workshop material automatic weighing data management method based on artificial intelligence;
FIG. 2 is a schematic flow chart of the automatic weighing data management system for workshop materials based on artificial intelligence.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions: the automatic weighing data management method for workshop materials based on artificial intelligence comprises the following steps:
s1, acquiring the number of a batch of a material to be measured and the processing flow of the current time, and acquiring the time period from the entering of the material to be measured to the exiting of the weighing apparatus, wherein the time period is recorded as a dynamic weighing interval; acquiring monitoring information of a built-in sensor of the weighing apparatus in a dynamic weighing interval in a dynamic material weighing process in real time through the built-in sensor of the weighing apparatus, wherein the monitoring information comprises detection data respectively corresponding to different times of the vibration sensor and the weighing sensor in the dynamic weighing process;
In the step S1, the dynamic weighing interval is marked as [ T1, T2]; recording detection data corresponding to time T of a vibration sensor in monitoring information of a built-in sensor of the weighing apparatus as Zt, wherein T is E [ T1, T2]; the detection data corresponding to the time t of the weighing sensor in the monitoring information of the built-in sensor of the weighing apparatus is recorded as Ct;
s2, dividing the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data, and judging the relevance among the data fragments divided by different sensor monitoring information; analyzing abnormal deviation of weighing states among the associated data segments, and predicting weighing values of the weighing materials in the batch of the materials to be measured by combining the associated data segments with the minimum abnormal deviation values of the weighing states to obtain weighing values corresponding to the batch of the materials to be measured in the current processing flow;
the method for dividing the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process in the S2 comprises the following steps:
s201, acquiring vibration sensor monitoring data corresponding to different time points in sensor monitoring information in a dynamic weighing interval in a dynamic weighing process, and constructing a monitoring data pair by each monitoring data and the corresponding time point, wherein tz is one time point in the dynamic weighing interval, and Atz represents the data monitored by the vibration sensor at the time point tz in the dynamic weighing process;
S202, marking coordinate points corresponding to the monitoring data obtained in the S201 in a first plane rectangular coordinate system, and connecting adjacent marking points in the first plane rectangular coordinate system to obtain a vibration amplitude line graph, wherein the first plane rectangular coordinate system is constructed by taking time as an x axis and vibration amplitude monitored by a vibration sensor as a y axis;
s203, marking each relation mutation node in the vibration amplitude line graph, wherein the relation mutation node is a turning point of converting the data in the vibration amplitude line graph from an increasing relation to a decreasing relation or from the decreasing relation to the increasing relation, the time corresponding to the relation mutation node is taken as a cutting position, the vibration amplitude line graph is divided into a plurality of data fragments, and the number of the divided data fragments is equal to the number of the corresponding relation mutation nodes plus one;
s204, constructing a second plane rectangular coordinate system, and constructing a weighing data line graph according to the method in S201-S202, wherein the second plane rectangular coordinate system is constructed by taking time as a horizontal axis and monitoring data of a weighing sensor as a vertical axis; taking the time corresponding to the relation mutation node obtained in the step S203 as a cutting position, and dividing the weighing data line graph into a plurality of data fragments;
The method for judging the relevance between the data segments divided by the monitoring information of the different sensors in the S2 comprises the following steps:
s211, acquiring data fragments corresponding to the vibration amplitude line graph in S203 and data fragments corresponding to the weighing data line graph in S204, wherein each data fragment corresponds to a time interval, binding two data fragments with the same corresponding time interval in the data fragments corresponding to the vibration amplitude line graph and the weighing data line graph, and each binding result corresponds to the data fragment corresponding to one weighing data line graph and the data fragment corresponding to one vibration amplitude line graph respectively; the data segment corresponding to the weighing data line graph corresponding to the ith binding result is marked as FCi, and the data segment corresponding to the vibration amplitude line graph corresponding to the ith binding result is marked as FZi;
s212, acquiring a binding association value between FCi and FZi in the ith binding result, which is marked as Gi,
the gi=1/(i 2-i 1) ·ζ b=i1 b=i2 |FCi（b）-H[FZi（b）]|db，
Wherein i1 represents the minimum value of the corresponding time interval of the data segment in the ith binding result, i2 represents the maximum value of the corresponding time interval of the data segment in the ith binding result, FCi (b) represents the corresponding weighing data in FCi when the time is b, FZi (b) represents the corresponding vibration amplitude in FZi when the time is b, H [ FZi (b) ] represents the function value after conversion of FZi (b),
H[FZi(b)]=[FCi(i2)-FCi(i1)]/[FZi(i2)-FZi(i1)]·{FZi(b)-FZi(i1)}+FCi(i1)，
Wherein FCi (i 2) represents the corresponding weighing data in time i2 and FCi, FCi (i 1) represents the corresponding weighing data in time i1 and FCi, FZi (i 2) represents the corresponding vibration amplitude in time i2 and FZi, and FZi (i 1) represents the corresponding vibration amplitude in time i1 and FZi; default FZi (i 2) is not equal to FZi (i 1);
in this embodiment, H [ FZi (b) ] is used to convert the value interval corresponding to FZi into the value interval corresponding to FCi when b is different, so as to analyze the binding association value (deviation condition) between the two values;
s213, comparing Gi with a binding association threshold, wherein the binding association threshold is a preset constant in a database,
when Gi is greater than or equal to the binding association threshold, judging that the association relation between FCi and FZi in the ith binding result does not exist, and the sensor monitoring data in the bound data fragment is interfered by noise;
when Gi is smaller than the binding association threshold, it is determined that the association relationship exists between FCi and FZi in the ith binding result.
The method for predicting the weighing value of the weighing materials in the batch of the materials to be detected in the S2 comprises the following steps:
s221, acquiring a binding result with an association relationship, numbering the acquired binding result, and predicting a weighing result corresponding to the vibration amplitude of 0 according to a data segment in the kth binding result with the association relationship, and marking as CYk;
When the vibration amplitude is 0 in the data segment belonging to the vibration amplitude line diagram in the kth binding result with the association relation, acquiring a time point with the vibration amplitude of 0, and marking the time point as tsk, wherein CYk is equal to the weighing result when the time in the data segment belonging to the weighing data line diagram in the kth binding result with the association relation is tsk;
when the condition that the vibration amplitude is 0 does not exist in the data segment belonging to the vibration amplitude line graph in the kth binding result with the association relation, acquiring the corresponding time point when the amplitude is 0 on the straight line corresponding to the two endpoints in the data segment belonging to the vibration amplitude line graph, and recording the time point as tLk, wherein CYk is equal to the weighing result when the time is tsk on the straight line corresponding to the two endpoints in the data segment belonging to the weighing data line graph in the kth binding result with the association relation;
in the embodiment, the range of the vibration amplitude corresponding to the vibration sensor is positive number, 0 and negative number;
s222, obtaining a weighing value corresponding to the current processing flow of the batch of the material to be measured, wherein the weighing value corresponding to the current processing flow of the batch of the material to be measured is equal to the average value of the predicted values of the weighing results when the vibration amplitudes corresponding to the binding results with the association relations are 0.
S3, inquiring a weighing result corresponding to the number of the batch of the material to be measured in the previous processing flow in a historical weighing database, marking the weighing result as reference weighing information, acquiring execution state information of the weighing instrument when the reference weighing information is acquired in the database, combining the execution state information of the weighing instrument when the weighing value corresponding to the current processing flow of the batch of the material to be measured is acquired, and predicting the theoretical weighing deviation amount of the instrument existing in the weighing value corresponding to the current processing flow of the batch of the material to be measured;
in the step S3, in the process of acquiring the execution state information of the weighing apparatus, acquiring the starting time tq of weighing the batch of the material to be measured in the corresponding processing flow by the weighing apparatus and the time tg of the last zero-resetting calibration operation executed by the corresponding weighing apparatus; recording weighing data corresponding to time tm of the weighing apparatus in a time period from tg to tq as Ctm, and enabling corresponding execution state information of the weighing apparatus to be ≡ tm=tg tm=tq Ctmdtm, tm e [ tg, tq]And tg is less than or equal to tq;
the method for predicting the theoretical weighing deviation amount of the instrument, which exists in the weighing value corresponding to the current processing flow, of the batch of the material to be detected in the S3 comprises the following steps:
s311, obtaining deviation weighing intervals corresponding to different execution state information of the weighing apparatus in the database pre-manufactured form, marking the deviation weighing intervals corresponding to the execution state information of the weighing apparatus corresponding to the reference weighing information as [ Cpc1, cpc2], marking the deviation weighing intervals corresponding to the execution state information of the weighing apparatus corresponding to the current processing flow of the batch of materials to be tested as [ Cpd1, cpd2],
Wherein Cpc1 represents the minimum value of the corresponding weighing deviation amount when the execution state information of the weighing apparatus in the database is the execution state information of the weighing apparatus corresponding to the reference weighing information (in this embodiment, when the execution state information of the weighing apparatus reaches the execution state information of the weighing apparatus corresponding to the reference weighing information by detecting that the execution state information of the weighing apparatus is the execution state information of the weighing apparatus, the corresponding weighing deviation amount is obtained by the difference between the indication number and 0 on the weighing apparatus under the condition that continuous weighing is stopped); cpc2 represents that the execution state information of the weighing instrument in the database is the maximum value of the corresponding weighing deviation amount when the weighing instrument is corresponding to the execution state information of the weighing instrument by referring to the weighing information; cpd1 represents the minimum value of the corresponding weighing deviation amount when the execution state information of the weighing instrument in the database is the execution state information of the weighing instrument corresponding to the current processing flow of the material batch to be measured; cpd2 represents the maximum value of corresponding weighing deviation amount when the execution state information of the weighing instrument in the database is the execution state information of the weighing instrument corresponding to the current processing flow of the material batch to be measured;
s312, obtaining a predicted value of the theoretical weighing deviation of the instrument existing in the weighing value corresponding to the current processing flow of the batch of the material to be measured, and recording the predicted value as [ min { Cpd1-Cpc1, cpd2-Cpc2}, max { Cpd1-Cpc1, cpd2-Cpc2} ],
Where min { Cpd1-Cpc1, cpd2-Cpc2} represents the minimum of Cpd1-Cpc1 and Cpd2-Cpc2 and max { Cpd1-Cpc1, cpd2-Cpc2} represents the maximum of Cpd1-Cpc1 and Cpd2-Cpc 2.
S4, according to a theoretical weighing value corresponding to the current processing flow of the material batch to be measured and an appliance theoretical weighing deviation value existing in the corresponding weighing value, obtaining a theoretical weighing fluctuation interval corresponding to the current processing flow of the material batch to be measured; the theoretical weighing value of the batch of the material to be measured corresponding to the current processing flow is obtained by inquiring a database preset form;
in the step S4, the theoretical weighing fluctuation interval of the batch of the material to be measured corresponding to the current processing flow is recorded as [ d1+d2, d1+d3], wherein D1 represents the theoretical weighing value of the batch of the material to be measured corresponding to the current processing flow, D2 represents the minimum value of the theoretical weighing deviation amount of the instrument existing in the weighing value corresponding to the current processing flow, and D3 represents the maximum value of the theoretical weighing deviation amount of the batch of the material to be measured in the instrument existing in the weighing value corresponding to the current processing flow;
s5, judging whether the weighing value of the material batch to be measured corresponding to the current processing flow is abnormal or not according to the weighing value of the material batch to be measured corresponding to the current processing flow and the corresponding theoretical weighing fluctuation interval, stopping continuously weighing the material in an abnormal state, carrying out zero resetting calibration on the weighing instrument, and dynamically weighing the weight of the material batch to be measured corresponding to the current processing flow again before inserting the material batch to be measured in the abnormal state into other non-weighed material batches; the number of the weighed material batches executed in the time interval of executing zero calibration on the weighing apparatus in two adjacent times is larger than n, and n is more than or equal to 1;
S5, judging whether the weighing value of the batch of the material to be measured corresponding to the current processing flow is abnormal, acquiring the weighing value of the batch of the material to be measured corresponding to the current processing flow and a corresponding theoretical weighing fluctuation interval,
when the weighing value corresponding to the material batch to be measured in the current processing flow belongs to the corresponding theoretical weighing fluctuation interval, judging that the weighing value corresponding to the material batch to be measured in the current processing flow is normal;
when the weighing value corresponding to the material batch to be measured in the current processing flow does not belong to the corresponding theoretical weighing fluctuation interval, judging that the weighing value corresponding to the material batch to be measured in the current processing flow is abnormal.
In the embodiment, the theoretical weighing value corresponding to the current processing flow of the batch of the material to be measured is obtained according to the weighing ratio relation of the same material in different flows in the historical data;
if the type of the material to be measured is P, the set formed by the weighing results of the material to be measured, which correspond to the current processing flow, is { P } 1 ，P 2 ，...P n ，...P n1 N1 represents the total number of processing flows of the material to be detected before the current processing flow, P n Representing a weighing result of the material to be measured corresponding to the nth processing flow;
the theoretical weighing value corresponding to the current processing flow of the batch of the material to be measured is recorded as 1/n1 ·Σ n=1 n=n1 P n G { n, n1+1}, wherein g { n, n1+1} represents an average value of a ratio of a weighing value at the n1+1-th process flow to a weighing value at the n-th process flow for each batch of the material type P in the history data;
in this embodiment, when the first processing flow is executed, the theoretical weighing value of the weighing result corresponding to the batch of the material to be measured is a constant preset according to the requirement of the customer order;
s6, managing weighing results of the material batches in different processing flows, and feeding back the material batches corresponding to the abnormal weighing results to an administrator;
and when the weighing results of the material batches in different processing flows are managed in the S6, if the same material batch is continuously weighed twice in the same processing flow, taking the state of the weighing result of the second time as the state of the corresponding material batch corresponding to the weighing value in the corresponding processing flow.
In this embodiment, if there are three material batches of A, B and C,
if the first material is weighed only once in the second processing flow and the state corresponding to the weighing result is abnormal, feeding back the material batch first to the manager;
if the second weighing is continuously carried out twice in the second processing flow, the state corresponding to the first weighing result is abnormal, and the state corresponding to the second weighing result is normal, the weighing result of the logistics batch B is judged to be normal, the material batch B is not required to be fed back to an administrator, the first weighing result corresponding to the second weighing result is used as an error weighing value, and the second weighing result is used as a correct weighing value;
If the third weighing result is abnormal, and the fourth weighing result is abnormal, and the third weighing result is abnormal.
As shown in fig. 2, the workshop material automatic weighing data management system based on artificial intelligence comprises the following modules:
the weighing data dynamic acquisition module acquires the serial number of the batch of the material to be measured and the processing flow of the current time, and acquires the time period from the entering of the material to be measured to the exiting of the weighing apparatus, and the time period is recorded as a dynamic weighing interval; acquiring monitoring information of a sensor arranged in the weighing apparatus in a dynamic weighing interval in a material dynamic weighing process in real time through the sensor arranged in the weighing apparatus;
the detection information segmentation and association analysis module is used for segmenting the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data and judging the association between the data segments after different sensor monitoring information segmentation; analyzing abnormal deviation of weighing states among the associated data segments, and predicting weighing values of the weighing materials in the batch of the materials to be measured by combining the associated data segments with the minimum abnormal deviation values of the weighing states to obtain weighing values corresponding to the batch of the materials to be measured in the current processing flow;
The theoretical weighing deviation prediction module is used for inquiring a weighing result corresponding to the previous processing flow of the batch number of the material to be measured in the historical weighing database, marking the weighing result as reference weighing information, acquiring the execution state information of the weighing instrument when the reference weighing information is acquired in the database, combining the execution state information of the weighing instrument when the weighing value corresponding to the current processing flow of the material batch to be measured is acquired, and predicting the theoretical weighing deviation of the instrument existing in the weighing value corresponding to the current processing flow of the material batch to be measured;
the weighing fluctuation analysis module obtains a theoretical weighing fluctuation interval corresponding to the material batch to be measured in the current processing flow according to a theoretical weighing value corresponding to the material batch to be measured in the current processing flow and an appliance theoretical weighing deviation value existing in the corresponding weighing value;
the zeroing calibration operation management module judges whether the weighing value of the material batch to be measured corresponding to the current processing flow is abnormal or not according to the weighing value of the material batch to be measured corresponding to the current processing flow and the corresponding theoretical weighing fluctuation interval, stops continuously weighing the material in an abnormal state, performs zeroing calibration on the weighing apparatus, and dynamically weighs the material batch to be measured again corresponding to the current processing flow before inserting the material batch to be measured in the abnormal state into other non-weighed material batches;
The abnormal feedback module is used for managing weighing results of the material batches in different processing flows and feeding back the material batches corresponding to the abnormal weighing results to an administrator.
The detection information segmentation and association analysis module comprises a data segment dividing unit, an association analysis unit and a weighing prediction unit,
the data segment dividing unit divides the segments of the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data;
the relevance analysis unit judges relevance among the data fragments divided by the monitoring information of different sensors;
the weighing prediction unit analyzes the abnormal deviation of the weighing state between the associated data segments, predicts the weighing value of the weighing material in the batch of the material to be measured by combining the associated data segment with the minimum abnormal deviation value of the weighing state, and obtains the weighing value of the batch of the material to be measured corresponding to the current processing flow.
The embodiment also comprises another workshop material automatic weighing data management method based on artificial intelligence, wherein a particle swarm algorithm is introduced, and inertia weight is improved so as to improve global optimizing capability, and finally, the BP neural network has higher accuracy in dynamic weighing data processing; the specific contents are as follows:
In the particle swarm optimization (POS), all particles move in a search range, each particle is regarded as a solution of a problem, a population consisting of all particles is regarded as a solution vector, and the position of the particle is continuously adjusted to complete the search of an optimal solution in a search space.
In d-dimensional space, randomly generating an initial population with the number N:
formula (1): xi= (x) i 1 ，x i 2 ，...，x i d ），i=1,2,3,...N，
Where xi represents the position of the i-th particle in d-dimensional space;
the position and velocity updates of the particles are defined as follows:
formula (2): v id t+1 =w·v id t +c 1 r 1 （P id t -x id t ）+c 2 r 2 （P gd t -x id t ），
Formula (3): x is x id t+1 =x id t +v id t ，
In the formulas (2) and (3), v id t+1 Represents the velocity, v, of the ith particle at time t+1 id t The speed of the ith particle at time t is represented, w represents the weight, c1 and c2 are acceleration factors, and r1 and r2 are [0,1 ]]Random number x of (x) id t Indicating the position of the ith particle at time t, P id t Represents the optimal position searched by the ith particle at the moment t, P gd t Indicating the optimal position searched for in the whole at time t.
According to the basic formula, the particles continuously adjust the positions and the speeds of the particles to realize global search by tracking two extreme values, and when the optimal fitness value in the particles reaches a set target or the iteration number reaches a set value, the particles with the optimal fitness value jump out of the loop, so that the particles with the optimal fitness value are the optimal solution.
In the PSO algorithm, the inertia weight factor reflects the capability of the particle to inherit the last iteration speed, and determines the capability of the algorithm for global searching and local searching, so that a proper inertia weight is beneficial to balancing the capability of global searching and local searching.
The inertia weight factor generally adopts a random number rule, and although the randomness is improved, the current execution process cannot be reflected, so that the inertia weight factor is controllable by improving the inertia weight factor to be related to the current process state, and the searching speed and the searching precision of the PSO are further improved.
Fit in algorithm i (t) represents the fitness value of the ith particle at the t-th iteration, and worst (t) represents the worst fitness value of the particle at the t-th moment, and N is the size of the population.
The word (t) is defined as follows:
formula (4): worth (t) =min { fit ] i (t)|i=1,2,3,...N}，
By defining the inertial weights as follows, equation (5) is obtained:
when fit i (t)≤fit avg In the case of (t), the process of (c),
w i (t)=w max -[(w max -w min )·(fit i (t)-worst(t))]/[fit avg (t)-worst(t)]，
when fit i (t)≤fit avg At (t), w i (t)=w max ，
Wherein w is min 、w max Represents the maximum and minimum values of the inertia weight w, and w is taken herein min =0.1，w max =0.6， fit avg (t) represents the currentTime-of-day average fitness value, fit i And (t) represents the fitness value at the current time. In the formula, the inertial weight of the particle changes as the objective function value of the particle changes.
The initial weights and thresholds of the neural network are optimized by analysis of the improved PSO algorithm. In order to meet PSO optimizing requirements, the inverse of the mean square error of the neural network is used as a fitness function for improving a PSO algorithm.
The PSO algorithm steps are as follows:
step 1): randomly initializing a population and an initial speed according to the limiting conditions of the particles;
step 2): calculating the fitness value of each particle according to the fitness function;
step 3): for each particle, use its fitness value fit i (t) and the individual extremum P id t Comparing, if fit i (t)> P id t Then use P id t Replace P id t Otherwise, reserving;
step 4): for each particle, use its fitness value fit i (t) and global extremum P gd t Comparing, if fit i (t)> P gd t Then use P id t Replace P gd t Otherwise, reserving;
step 5): updating the velocity and position of the particles according to formulas (2) and (3);
step 6): and (5) ending when the optimal fitness value or the maximum iteration number is reached, otherwise, repeating the steps (2) - (5).
The method adopts the PSO-BP neural network based on improvement, reduces the complexity of the model, ensures the accuracy of the data result of dynamic weighing, and improves the material circulation efficiency.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. The workshop material automatic weighing data management method based on artificial intelligence is characterized by comprising the following steps of:
s1, acquiring the number of a batch of a material to be measured and the processing flow of the current time, and acquiring the time period from the entering of the material to be measured to the exiting of the weighing apparatus, wherein the time period is recorded as a dynamic weighing interval; acquiring monitoring information of a built-in sensor of the weighing apparatus in a dynamic weighing interval in a dynamic material weighing process in real time through the built-in sensor of the weighing apparatus, wherein the monitoring information comprises detection data respectively corresponding to different times of the vibration sensor and the weighing sensor in the dynamic weighing process;
S2, dividing the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data, and judging the relevance among the data fragments divided by different sensor monitoring information; analyzing abnormal deviation of weighing states among the associated data segments, and predicting weighing values of the weighing materials in the batch of the materials to be measured by combining the associated data segments with the minimum abnormal deviation values of the weighing states to obtain weighing values corresponding to the batch of the materials to be measured in the current processing flow;
s3, inquiring a weighing result corresponding to the number of the batch of the material to be measured in the previous processing flow in a historical weighing database, marking the weighing result as reference weighing information, acquiring execution state information of the weighing instrument when the reference weighing information is acquired in the database, combining the execution state information of the weighing instrument when the weighing value corresponding to the current processing flow of the batch of the material to be measured is acquired, and predicting the theoretical weighing deviation amount of the instrument existing in the weighing value corresponding to the current processing flow of the batch of the material to be measured;
s4, according to a theoretical weighing value corresponding to the current processing flow of the material batch to be measured and an appliance theoretical weighing deviation value existing in the corresponding weighing value, obtaining a theoretical weighing fluctuation interval corresponding to the current processing flow of the material batch to be measured; the theoretical weighing value of the batch of the material to be measured corresponding to the current processing flow is obtained by inquiring a database preset form;
S5, judging whether the weighing value of the material batch to be measured corresponding to the current processing flow is abnormal or not according to the weighing value of the material batch to be measured corresponding to the current processing flow and the corresponding theoretical weighing fluctuation interval, stopping continuously weighing the material in an abnormal state, carrying out zero resetting calibration on the weighing instrument, and dynamically weighing the weight of the material batch to be measured corresponding to the current processing flow again before inserting the material batch to be measured in the abnormal state into other non-weighed material batches; the number of the weighed material batches executed in the time interval of executing zero calibration on the weighing apparatus in two adjacent times is larger than n, and n is more than or equal to 1;
s6, managing weighing results of the material batches in different processing flows, and feeding back the material batches corresponding to the abnormal weighing results to an administrator;
in the step S1, the dynamic weighing interval is marked as [ T1, T2]; recording detection data corresponding to time T of a vibration sensor in monitoring information of a built-in sensor of the weighing apparatus as Zt, wherein T is E [ T1, T2]; the detection data corresponding to the time t of the weighing sensor in the monitoring information of the built-in sensor of the weighing apparatus is recorded as Ct;
the method for dividing the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process in the S2 comprises the following steps:
S201, acquiring vibration sensor monitoring data corresponding to different time points in sensor monitoring information in a dynamic weighing interval in a dynamic weighing process, and constructing a monitoring data pair by each monitoring data and the corresponding time point, wherein tz is one time point in the dynamic weighing interval, and Atz represents the data monitored by the vibration sensor at the time point tz in the dynamic weighing process;
s202, marking coordinate points corresponding to the monitoring data obtained in the S201 in a first plane rectangular coordinate system, and connecting adjacent marking points in the first plane rectangular coordinate system to obtain a vibration amplitude line graph, wherein the first plane rectangular coordinate system is constructed by taking time as an x axis and vibration amplitude monitored by a vibration sensor as a y axis;
s203, marking each relation mutation node in the vibration amplitude line graph, wherein the relation mutation node is a turning point of converting the data in the vibration amplitude line graph from an increasing relation to a decreasing relation or from the decreasing relation to the increasing relation, the time corresponding to the relation mutation node is taken as a cutting position, the vibration amplitude line graph is divided into a plurality of data fragments, and the number of the divided data fragments is equal to the number of the corresponding relation mutation nodes plus one;
S204, constructing a second plane rectangular coordinate system, and constructing a weighing data line graph according to the method in S201-S202, wherein the second plane rectangular coordinate system is constructed by taking time as a horizontal axis and monitoring data of a weighing sensor as a vertical axis; taking the time corresponding to the relation mutation node obtained in the step S203 as a cutting position, and dividing the weighing data line graph into a plurality of data fragments;
the method for judging the relevance between the data segments divided by the monitoring information of the different sensors in the S2 comprises the following steps:
s211, acquiring data fragments corresponding to the vibration amplitude line graph in S203 and data fragments corresponding to the weighing data line graph in S204, wherein each data fragment corresponds to a time interval, binding two data fragments with the same corresponding time interval in the data fragments corresponding to the vibration amplitude line graph and the weighing data line graph, and each binding result corresponds to the data fragment corresponding to one weighing data line graph and the data fragment corresponding to one vibration amplitude line graph respectively; the data segment corresponding to the weighing data line graph corresponding to the ith binding result is marked as FCi, and the data segment corresponding to the vibration amplitude line graph corresponding to the ith binding result is marked as FZi;
S212, acquiring a binding association value between FCi and FZi in the ith binding result, which is marked as Gi,
the gi=1/(i 2-i 1) ·ζ b=i1 b=i2 |FCi（b）-H[FZi（b）]|db，
Wherein i1 represents the minimum value of the corresponding time interval of the data segment in the ith binding result, i2 represents the maximum value of the corresponding time interval of the data segment in the ith binding result, FCi (b) represents the corresponding weighing data in FCi when the time is b, FZi (b) represents the corresponding vibration amplitude in FZi when the time is b, H [ FZi (b) ] represents the function value after conversion of FZi (b),
H[FZi(b)]=[FCi(i2)-FCi(i1)]/[FZi(i2)-FZi(i1)]·{FZi(b)-FZi(i1)}+FCi(i1)，
wherein FCi (i 2) represents the corresponding weighing data in time i2 and FCi, FCi (i 1) represents the corresponding weighing data in time i1 and FCi, FZi (i 2) represents the corresponding vibration amplitude in time i2 and FZi, and FZi (i 1) represents the corresponding vibration amplitude in time i1 and FZi; default FZi (i 2) is not equal to FZi (i 1);
s213, comparing Gi with a binding association threshold, wherein the binding association threshold is a preset constant in a database,
when Gi is greater than or equal to the binding association threshold, judging that the association relation between FCi and FZi in the ith binding result does not exist, and the sensor monitoring data in the bound data fragment is interfered by noise;
when Gi is smaller than the binding association threshold, it is determined that the association relationship exists between FCi and FZi in the ith binding result.
2. The automatic weighing data management method for workshop materials based on artificial intelligence according to claim 1, wherein: the method for predicting the weighing value of the weighing materials in the batch of the materials to be detected in the S2 comprises the following steps:
s221, acquiring a binding result with an association relationship, numbering the acquired binding result, and predicting a weighing result corresponding to the vibration amplitude of 0 according to a data segment in the kth binding result with the association relationship, and marking as CYk;
when the vibration amplitude is 0 in the data segment belonging to the vibration amplitude line diagram in the kth binding result with the association relation, acquiring a time point with the vibration amplitude of 0, and marking the time point as tsk, wherein CYk is equal to the weighing result when the time in the data segment belonging to the weighing data line diagram in the kth binding result with the association relation is tsk;
when the condition that the vibration amplitude is 0 does not exist in the data segment belonging to the vibration amplitude line graph in the kth binding result with the association relation, acquiring the corresponding time point when the amplitude is 0 on the straight line corresponding to the two endpoints in the data segment belonging to the vibration amplitude line graph, and recording the time point as tLk, wherein CYk is equal to the weighing result when the time is tsk on the straight line corresponding to the two endpoints in the data segment belonging to the weighing data line graph in the kth binding result with the association relation;
S222, obtaining a weighing value corresponding to the current processing flow of the batch of the material to be measured, wherein the weighing value corresponding to the current processing flow of the batch of the material to be measured is equal to the average value of the predicted values of the weighing results when the vibration amplitudes corresponding to the binding results with the association relations are 0.
3. The automatic weighing data management method for workshop materials based on artificial intelligence according to claim 1, wherein: in the step S3, in the process of acquiring the execution state information of the weighing apparatus, acquiring the starting time tq of weighing the batch of the material to be measured in the corresponding processing flow by the weighing apparatus and the time tg of the last zero-resetting calibration operation executed by the corresponding weighing apparatus; recording weighing data corresponding to time tm of the weighing apparatus in a time period from tg to tq as Ctm, and enabling corresponding execution state information of the weighing apparatus to be ≡ tm=tg tm= tq Ctmdtm, tm e [ tg, tq]And tg is less than or equal to tq;
the method for predicting the theoretical weighing deviation amount of the instrument, which exists in the weighing value corresponding to the current processing flow, of the batch of the material to be detected in the S3 comprises the following steps:
s311, obtaining deviation weighing intervals corresponding to different execution state information of the weighing apparatus in the database pre-manufactured form, marking the deviation weighing intervals corresponding to the execution state information of the weighing apparatus corresponding to the reference weighing information as [ Cpc1, cpc2], marking the deviation weighing intervals corresponding to the execution state information of the weighing apparatus corresponding to the current processing flow of the batch of materials to be tested as [ Cpd1, cpd2],
Wherein Cpc1 represents the minimum value of the corresponding weighing deviation amount when the execution state information of the weighing apparatus in the database corresponds to the execution state information of the weighing apparatus by referring to the weighing information; cpc2 represents that the execution state information of the weighing instrument in the database is the maximum value of the corresponding weighing deviation amount when the weighing instrument is corresponding to the execution state information of the weighing instrument by referring to the weighing information; cpd1 represents the minimum value of the corresponding weighing deviation amount when the execution state information of the weighing instrument in the database is the execution state information of the weighing instrument corresponding to the current processing flow of the material batch to be measured; cpd2 represents the maximum value of corresponding weighing deviation amount when the execution state information of the weighing instrument in the database is the execution state information of the weighing instrument corresponding to the current processing flow of the material batch to be measured;
s312, obtaining a predicted value of the theoretical weighing deviation of the instrument existing in the weighing value corresponding to the current processing flow of the batch of the material to be measured, and recording the predicted value as [ min { Cpd1-Cpc1, cpd2-Cpc2}, max { Cpd1-Cpc1, cpd2-Cpc2} ],
where min { Cpd1-Cpc1, cpd2-Cpc2} represents the minimum of Cpd1-Cpc1 and Cpd2-Cpc2 and max { Cpd1-Cpc1, cpd2-Cpc2} represents the maximum of Cpd1-Cpc1 and Cpd2-Cpc 2.
4. The automatic weighing data management method for workshop materials based on artificial intelligence according to claim 1, wherein: in the step S4, the theoretical weighing fluctuation interval of the batch of the material to be measured corresponding to the current processing flow is recorded as [ d1+d2, d1+d3], wherein D1 represents the theoretical weighing value of the batch of the material to be measured corresponding to the current processing flow, D2 represents the minimum value of the theoretical weighing deviation amount of the instrument existing in the weighing value corresponding to the current processing flow, and D3 represents the maximum value of the theoretical weighing deviation amount of the batch of the material to be measured in the instrument existing in the weighing value corresponding to the current processing flow;
S5, judging whether the weighing value of the batch of the material to be measured corresponding to the current processing flow is abnormal, acquiring the weighing value of the batch of the material to be measured corresponding to the current processing flow and a corresponding theoretical weighing fluctuation interval,
when the weighing value corresponding to the material batch to be measured in the current processing flow belongs to the corresponding theoretical weighing fluctuation interval, judging that the weighing value corresponding to the material batch to be measured in the current processing flow is normal;
when the weighing value corresponding to the material batch to be measured in the current processing flow does not belong to the corresponding theoretical weighing fluctuation interval, judging that the weighing value corresponding to the material batch to be measured in the current processing flow is abnormal.
5. The automatic weighing data management method for workshop materials based on artificial intelligence according to claim 1, wherein: and when the weighing results of the material batches in different processing flows are managed in the S6, if the same material batch is continuously weighed twice in the same processing flow, taking the state of the weighing result of the second time as the state of the corresponding material batch corresponding to the weighing value in the corresponding processing flow.
6. Workshop material automatic weighing data management system based on artificial intelligence, the system is realized by applying the workshop material automatic weighing data management method based on artificial intelligence as claimed in any one of claims 1 to 5, and the system is characterized in that: the system comprises the following modules:
The weighing data dynamic acquisition module acquires the serial number of the batch of the material to be measured and the processing flow of the current time, and acquires the time period from the entering of the material to be measured to the exiting of the weighing apparatus, and the time period is recorded as a dynamic weighing interval; acquiring monitoring information of a sensor arranged in the weighing apparatus in a dynamic weighing interval in a material dynamic weighing process in real time through the sensor arranged in the weighing apparatus;
the detection information segmentation and association analysis module is used for segmenting the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data and judging the association between the data segments after different sensor monitoring information segmentation; analyzing abnormal deviation of weighing states among the associated data segments, and predicting weighing values of the weighing materials in the batch of the materials to be measured by combining the associated data segments with the minimum abnormal deviation values of the weighing states to obtain weighing values corresponding to the batch of the materials to be measured in the current processing flow;
the theoretical weighing deviation prediction module is used for inquiring a weighing result corresponding to the previous processing flow of the batch number of the material to be measured in the historical weighing database, marking the weighing result as reference weighing information, acquiring the execution state information of the weighing instrument when the reference weighing information is acquired in the database, combining the execution state information of the weighing instrument when the weighing value corresponding to the current processing flow of the material batch to be measured is acquired, and predicting the theoretical weighing deviation of the instrument existing in the weighing value corresponding to the current processing flow of the material batch to be measured;
The weighing fluctuation analysis module obtains a theoretical weighing fluctuation interval corresponding to the material batch to be measured in the current processing flow according to a theoretical weighing value corresponding to the material batch to be measured in the current processing flow and an appliance theoretical weighing deviation value existing in the corresponding weighing value;
the zeroing calibration operation management module judges whether the weighing value of the material batch to be measured corresponding to the current processing flow is abnormal or not according to the weighing value of the material batch to be measured corresponding to the current processing flow and the corresponding theoretical weighing fluctuation interval, stops continuously weighing the material in an abnormal state, performs zeroing calibration on the weighing apparatus, and dynamically weighs the material batch to be measured again corresponding to the current processing flow before inserting the material batch to be measured in the abnormal state into other non-weighed material batches;
the abnormal feedback module is used for managing weighing results of the material batches in different processing flows and feeding back the material batches corresponding to the abnormal weighing results to an administrator.
7. The automatic weighing data management system for workshop materials based on artificial intelligence according to claim 6, wherein: the detection information segmentation and association analysis module comprises a data segment dividing unit, an association analysis unit and a weighing prediction unit,
The data segment dividing unit divides the segments of the sensor monitoring information in the dynamic weighing interval in the dynamic weighing process according to the numerical value change condition of the detection data;
the relevance analysis unit judges relevance among the data fragments divided by the monitoring information of different sensors;
the weighing prediction unit analyzes the abnormal deviation of the weighing state between the associated data segments, predicts the weighing value of the weighing material in the batch of the material to be measured by combining the associated data segment with the minimum abnormal deviation value of the weighing state, and obtains the weighing value of the batch of the material to be measured corresponding to the current processing flow.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311347942.2A CN117077993B (en) | 2023-10-18 | 2023-10-18 | Workshop material automatic weighing data management system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311347942.2A CN117077993B (en) | 2023-10-18 | 2023-10-18 | Workshop material automatic weighing data management system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117077993A CN117077993A (en) | 2023-11-17 |
| CN117077993B true CN117077993B (en) | 2024-01-26 |
Family
ID=88713889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311347942.2A Active CN117077993B (en) | 2023-10-18 | 2023-10-18 | Workshop material automatic weighing data management system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117077993B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4534428A (en) * | 1983-08-11 | 1985-08-13 | Package Machinery Co. | Vibratory feeder control for a weighing system |
| JP2000180256A (en) * | 1998-12-18 | 2000-06-30 | Ishida Co Ltd | Weighing device |
| DE10114481A1 (en) * | 2001-03-24 | 2002-09-26 | Schenck Process Gmbh | Dynamic measurement of axle load or weight of vehicle involves comparing dynamic force sensor signal profile in measurement window with vibration-independent reference signal profile |
| CN106268400A (en) * | 2016-09-23 | 2017-01-04 | 中化重庆涪陵化工有限公司 | Automatic batching system |
| CN108871526A (en) * | 2018-05-31 | 2018-11-23 | 运城学院 | A kind of monitoring weighing platform vibrates the dynamic weighing method of pre- subtraction |
| CN112304413A (en) * | 2020-09-28 | 2021-02-02 | 梅特勒-托利多(常州)精密仪器有限公司 | Method and device for detecting state of weighing sensor |
| CN112816045A (en) * | 2020-12-30 | 2021-05-18 | 北京万集科技股份有限公司 | Dynamic weighing method and dynamic weighing device for vehicle |
| CN114166328A (en) * | 2021-12-06 | 2022-03-11 | 深圳市杰曼科技股份有限公司 | Method for self-adjusting weighing sensor |
| CN116380228A (en) * | 2023-03-14 | 2023-07-04 | 山东钢铁集团日照有限公司 | Method, system, terminal and storage medium for monitoring operation of weighing apparatus |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10024986C2 (en) * | 2000-05-19 | 2002-03-07 | Sartorius Gmbh | Electronic weighing sensor |
-
2023
- 2023-10-18 CN CN202311347942.2A patent/CN117077993B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4534428A (en) * | 1983-08-11 | 1985-08-13 | Package Machinery Co. | Vibratory feeder control for a weighing system |
| JP2000180256A (en) * | 1998-12-18 | 2000-06-30 | Ishida Co Ltd | Weighing device |
| DE10114481A1 (en) * | 2001-03-24 | 2002-09-26 | Schenck Process Gmbh | Dynamic measurement of axle load or weight of vehicle involves comparing dynamic force sensor signal profile in measurement window with vibration-independent reference signal profile |
| CN106268400A (en) * | 2016-09-23 | 2017-01-04 | 中化重庆涪陵化工有限公司 | Automatic batching system |
| CN108871526A (en) * | 2018-05-31 | 2018-11-23 | 运城学院 | A kind of monitoring weighing platform vibrates the dynamic weighing method of pre- subtraction |
| CN112304413A (en) * | 2020-09-28 | 2021-02-02 | 梅特勒-托利多(常州)精密仪器有限公司 | Method and device for detecting state of weighing sensor |
| CN112816045A (en) * | 2020-12-30 | 2021-05-18 | 北京万集科技股份有限公司 | Dynamic weighing method and dynamic weighing device for vehicle |
| CN114166328A (en) * | 2021-12-06 | 2022-03-11 | 深圳市杰曼科技股份有限公司 | Method for self-adjusting weighing sensor |
| CN116380228A (en) * | 2023-03-14 | 2023-07-04 | 山东钢铁集团日照有限公司 | Method, system, terminal and storage medium for monitoring operation of weighing apparatus |
Non-Patent Citations (4)
| Title |
|---|
| 不停车计重收费系统的动态称重传感器优化方法研究;李浩等;科学技术与工程;303-306+316 * |
| 基于向量分割的动态称重模型优化方法;李浩;宿金菲;赵敏慧;梁杰;;公路交通科技(07);第101-107页 * |
| 基于神经网络自适应滤波的车辆动态称重系统研究;张瑞;吕文红;张瑞玺;;公路交通科技(07);第第138-141+146138-141+146页 * |
| 浅谈称重传感器技术动向、发展趋势和产业方向;刘九卿;;衡器(06);第1-5页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117077993A (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10809153B2 (en) | Detecting apparatus, detection method, and program | |
| US5511004A (en) | Diagnostic method for an evolutionary process | |
| US5251144A (en) | System and method utilizing a real time expert system for tool life prediction and tool wear diagnosis | |
| Abdulshahed et al. | The application of ANFIS prediction models for thermal error compensation on CNC machine tools | |
| Iverson et al. | Run-time statistical estimation of task execution times for heterogeneous distributed computing | |
| US20090187381A1 (en) | Novelty detection | |
| JP6887361B2 (en) | Monitoring target selection device, monitoring target selection method, and program | |
| US20220011766A1 (en) | Error-based method for calculating a remaining useful life of an apparatus | |
| CN116380445A (en) | Equipment state diagnosis method and related device based on vibration waveform | |
| CN108664000A (en) | A kind of alumina producing evaporation process steady state detecting method for use and system | |
| CN117077993B (en) | Workshop material automatic weighing data management system and method based on artificial intelligence | |
| CN117270514B (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
| Zhang et al. | Self-organising neural networks for automated machinery monitoring systems | |
| CN1782672A (en) | Method and apparatus for improved fault detection in power generation equipment | |
| CN114637620B (en) | Database system abnormal classification prediction method based on SVM algorithm | |
| US7443395B2 (en) | Multi-variable operations | |
| US20180087489A1 (en) | Method for windmill farm monitoring | |
| Wang et al. | Predictive maintenance and sensitivity analysis for equipment with multiple quality states | |
| CN113408076A (en) | Small sample mechanical residual life prediction method based on support vector machine model | |
| US20220413480A1 (en) | Time series data processing method | |
| CN112912807A (en) | Abnormality diagnosis device | |
| Scrimieri et al. | Modular reconfiguration of flexible production systems using machine learning and performance estimates | |
| CN117330963B (en) | Energy storage power station fault detection method, system and equipment | |
| CN116661522B (en) | Intelligent temperature regulation and control method for temperature change test box based on data processing | |
| El-Férik et al. | A tractable class of maximal hedging policies in multi-part manufacturing systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |