CN117391427A - Medical instrument production intelligent supervision system based on artificial intelligence - Google Patents
Medical instrument production intelligent supervision system based on artificial intelligence Download PDFInfo
- Publication number
- CN117391427A CN117391427A CN202310804673.1A CN202310804673A CN117391427A CN 117391427 A CN117391427 A CN 117391427A CN 202310804673 A CN202310804673 A CN 202310804673A CN 117391427 A CN117391427 A CN 117391427A
- Authority
- CN
- China
- Prior art keywords
- analysis
- deviation
- value
- coefficient
- production
- 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.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 217
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 214
- 238000000034 method Methods 0.000 claims abstract description 186
- 238000012544 monitoring process Methods 0.000 claims abstract description 77
- 238000012545 processing Methods 0.000 claims abstract description 56
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 230000002159 abnormal effect Effects 0.000 claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 23
- 230000005856 abnormality Effects 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims description 23
- 239000000428 dust Substances 0.000 claims description 16
- 230000006399 behavior Effects 0.000 claims description 12
- 238000012423 maintenance Methods 0.000 claims description 11
- 238000012797 qualification Methods 0.000 claims description 7
- 239000002699 waste material Substances 0.000 claims description 7
- 239000002351 wastewater Substances 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 230000002411 adverse Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 239000002912 waste gas Substances 0.000 claims description 4
- 230000001788 irregular Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 description 27
- 238000007726 management method Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 239000007789 gas Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000010561 standard procedure Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- -1 calibrators Substances 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Factory Administration (AREA)
Abstract
The invention belongs to the technical field of medical instrument production supervision, in particular to an intelligent medical instrument production supervision system based on artificial intelligence, which comprises a server, a procedure deviation supervision analysis module, a procedure monitoring, identification and evaluation module and a procedure abnormality comprehensive judgment module; according to the invention, the corresponding analysis objects are subjected to process deviation supervision analysis so as to effectively control the process equipment and the environment of the region, the region of the corresponding analysis objects is monitored and risk operation is identified, personnel operation supervision identification of each process is realized, the process abnormal condition analysis results are more accurate through comprehensive judgment and analysis of the corresponding analysis objects, safe and efficient production of each process of the corresponding production line is effectively ensured, the quality of daily processed products is judged through quality detection of medical instrument products of the corresponding production line, the optimal yield range of the corresponding production line is determined, and the follow-up scientific planning of the daily processing efficiency of the corresponding production line is realized.
Description
Technical Field
The invention relates to the technical field of medical instrument production supervision, in particular to an intelligent medical instrument production supervision system based on artificial intelligence.
Background
Medical instruments refer to instruments, devices, appliances, in-vitro diagnostic reagents, calibrators, materials and other similar or related articles which are directly or indirectly used for a human body, and comprise medical devices and medical consumables, and the purpose is mainly to diagnose, prevent, monitor, treat or relieve diseases, and in the production process of the medical instruments, the related production line of medical instrument products is required to be supervised;
at present, when the production line of the corresponding medical instrument products is monitored, the various working procedures of the corresponding production line are difficult to comprehensively monitor, control and control, and the various working procedures are comprehensively evaluated and analyzed to timely and accurately early warn the abnormal working procedures, so that the safe and efficient production of the various working procedures of the corresponding production line is not easy to be ensured, the daily product quality condition of the corresponding production line is difficult to be accurately evaluated and the subsequent daily yield is scientifically planned, and the production efficiency and the product quality of the medical instrument products produced by the corresponding production line are not easy to be ensured;
in view of the above technical drawbacks, a solution is now proposed.
Disclosure of Invention
The invention aims to provide an intelligent monitoring system for medical instrument production based on artificial intelligence, which solves the problems that in the prior art, the process steps of a corresponding production line are difficult to comprehensively monitor, control and control, the safe and efficient production of the process steps of the corresponding production line is not easy to ensure, the daily product quality condition of the corresponding production line is difficult to accurately evaluate and scientifically plan the subsequent daily yield, and the production efficiency and the product quality are not easy to ensure.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an intelligent supervisory system for medical instrument production based on artificial intelligence comprises a server, a procedure deviation supervisory analysis module, a procedure monitoring, identifying and evaluating module and a procedure abnormality comprehensive judging module; the method comprises the steps that a server obtains a production line of corresponding medical equipment and all production procedures of the corresponding production line, the corresponding production procedures are marked as analysis objects i, i= {1,2, …, n }, n represents the number of the production procedures in the corresponding production line and n is a natural number larger than 1; the process deviation supervision and analysis module acquires environment deviation data and equipment operation data corresponding to the analysis object i, performs process deviation supervision and analysis according to the environment deviation data and the equipment operation data, generates a deviation judgment symbol PL1 or PL2 of the analysis object i through the process deviation supervision and analysis, and sends the process deviation judgment symbol PL1 or PL2 to the process abnormality comprehensive judgment module through the server;
The process monitoring, identifying and evaluating module monitors the area where the corresponding analysis object i is located, identifies risk operation in the corresponding analysis object i based on the monitoring image, marks the corresponding operator as a top-grade operator, a good-grade operator or a bad-grade operator according to the risk operation in the corresponding analysis object i through analysis, generates a monitoring judgment symbol JK1 or JK2 of the corresponding analysis object i through analysis, and sends the monitoring judgment symbol JK1 or JK2 to the process anomaly comprehensive judgment module through a server; the process anomaly comprehensive judgment module carries out comprehensive judgment and analysis on the corresponding analysis object i, generates a process supervision abnormal signal or a process supervision normal signal through comprehensive judgment and analysis, and sends the process supervision abnormal signal or the process supervision normal signal to the background supervision terminal through the server.
Further, the specific analysis process of the process deviation supervision analysis comprises the following steps:
acquiring environment deviation data of an analysis object i, wherein the environment deviation data comprise an environment temperature deviation value, an environment humidity deviation value, an environment wind power deviation value and an environment dust deviation value of an area where the analysis object i is positioned, generating a deviation judgment symbol PL1 if at least one of the environment temperature deviation value, the environment humidity deviation value, the environment wind power deviation value and the environment dust deviation value exceeds a corresponding preset threshold value, carrying out normalization calculation on the environment temperature deviation value, the environment humidity deviation value, the environment wind power deviation value and the environment dust deviation value to obtain a primary deviation analysis coefficient, and carrying out numerical comparison on the primary deviation analysis coefficient and the preset primary deviation analysis coefficient threshold value if the environment temperature deviation value, the environment humidity deviation value, the environment wind power deviation value and the environment dust deviation value do not exceed the corresponding preset threshold value;
If the initial bias analysis coefficient exceeds a preset initial bias analysis coefficient threshold value, generating a deviation judgment symbol PL1; if the initial deviation analysis coefficient does not exceed the preset initial deviation analysis coefficient threshold value, acquiring equipment operation data of the analysis object i, wherein the equipment operation data comprises a noise coefficient and a vibration coefficient generated in the operation process of production equipment corresponding to the analysis object i; if at least one of the noise coefficient and the vibration coefficient exceeds the corresponding preset threshold value, a deviation judging symbol PL1 is generated, if the noise coefficient and the vibration coefficient do not exceed the corresponding preset threshold value, a difference value of the noise coefficient compared with the corresponding preset threshold value and a difference value of the vibration coefficient compared with the corresponding preset threshold value are marked as a threshold difference value coefficient and a vibration threshold difference value coefficient respectively, the threshold difference value coefficient and the vibration threshold difference value coefficient are subjected to numerical calculation to obtain a device evaluation coefficient, the device evaluation coefficient is subjected to numerical comparison with a preset device evaluation coefficient threshold value, if the device evaluation coefficient does not exceed the preset device evaluation coefficient threshold value, a deviation judging symbol PL1 is generated, and if the device evaluation coefficient does not exceed the preset device evaluation coefficient threshold value, a deviation judging symbol PL2 is generated.
Further, the specific operation process of the process monitoring, identifying and evaluating module comprises the following steps:
Monitoring the region where the corresponding analysis object i is located through a monitoring camera, acquiring the action behaviors of operators in the region where the analysis object i is located through a monitoring image, identifying the action behaviors of the corresponding operators to mark action behaviors which do not meet the requirements of corresponding procedures, marking the action behaviors which do not meet the requirements of the corresponding procedures as risk operations, acquiring the operation types to which the corresponding risk operations belong and the operation risk coefficients of the corresponding operation types, multiplying the risk operation quantity of the corresponding operation types of the corresponding operators by the corresponding operation risk coefficients to obtain action judgment values, and summing the action judgment values of all the operation types of the corresponding operators to obtain action re-analysis values;
comparing the action re-analysis value with a preset action re-analysis value range in a numerical value mode, judging that the operation of a corresponding operator is very irregular and marked as a inferior operator if the action re-analysis value exceeds the maximum value of the preset action re-analysis value range, judging that the operation of the corresponding operator is good and marked as a good operator if the action re-analysis value is within the preset action re-analysis value range, and judging that the operation of the corresponding operator is excellent and marked as a superior operator if the action re-analysis value does not exceed the minimum value of the preset action re-analysis value range;
If the area where the analysis object i is located has inferior operators, generating a monitoring judgment symbol JK1; if no inferior operators exist in the area where the analysis object i is located, the number of the superior operators and the number of the superior operators are subjected to ratio calculation to obtain a monitoring identification coefficient, the monitoring identification coefficient is subjected to numerical comparison with a preset monitoring identification coefficient threshold value, a monitoring judgment symbol JK1 is generated if the monitoring identification coefficient exceeds the preset monitoring identification coefficient threshold value, and a monitoring judgment symbol JK2 is generated if the monitoring identification coefficient does not exceed the preset monitoring identification coefficient threshold value.
Further, the specific operation process of the process abnormality comprehensive judgment module comprises:
acquiring a process deviation judgment symbol PL1 or PL2 and a monitoring judgment symbol JK1 or JK2 corresponding to the analysis object i, and generating a process supervision abnormal signal corresponding to the analysis object i if PL1 n JK1, PL1 n JK2 or PL2 n JK1 are acquired; if PL 2U JK2 is obtained, acquiring waste water generation amount data, waste gas generation amount data and waste material generation amount data corresponding to the analysis object i, carrying out numerical calculation on the waste water generation amount data, the waste gas generation amount data and the waste material generation amount data to obtain a process abnormal value, carrying out ratio calculation on the process abnormal value and a medical instrument processing efficiency value corresponding to the analysis object i to obtain a process representation value, carrying out numerical comparison on the process representation value and a preset process representation threshold, generating a process supervision abnormal signal if the process representation value exceeds the preset process representation threshold, and otherwise generating a process supervision normal signal corresponding to the analysis object i.
Further, if the procedure supervision abnormal signal is generated, the corresponding analysis object i is marked as an nonstandard procedure, if the procedure supervision normal signal is generated, the corresponding analysis object i is marked as a standard procedure, and the ratio of the number of the nonstandard procedures to the number of the standard procedures in the corresponding production line is calculated to obtain a production supervision coefficient; and carrying out numerical comparison on the production supervision coefficient and a preset production supervision coefficient threshold value, if the production supervision coefficient exceeds the preset production supervision coefficient threshold value, generating a comprehensive maintenance and adjustment signal corresponding to the production line, and sending the comprehensive maintenance and adjustment signal to a background supervision terminal through a server.
Further, the server is in communication connection with the product quality detection summarizing module and the production efficiency scientific planning module, wherein the product quality detection summarizing module carries out quality detection on medical instrument products of corresponding production lines, marks products with all detection item data meeting preset data requirements as flawless products, and marks the corresponding medical instrument products as high-deviation products or low-deviation products through product difference analysis if the corresponding medical instrument products have detection item data which does not meet the preset data requirements;
Carrying out numerical calculation on the number of flawless products, the number of high-deviation products and the number of low-deviation products in the corresponding production line per day to obtain daily product quality coefficients of the corresponding processing days of the production line; the daily product quality coefficient is compared with a preset daily quality coefficient in a numerical value, if the daily product quality coefficient exceeds a preset daily product quality coefficient threshold value, a production line processing disqualification signal is generated, otherwise, a production line processing qualification signal is generated, and the production line processing disqualification signal or the production line processing qualification signal of the corresponding production line is sent to a background monitoring terminal through a server; the production efficiency scientific planning module carries out supervision planning analysis on the processing efficiency of the corresponding production line, determines the preferred yield range of the corresponding production line through analysis, and sends the preferred yield range to the background supervision terminal through the server.
Further, the specific analysis process of the product difference analysis is as follows:
the method comprises the steps of collecting the number of detection items which do not meet the preset data requirement in corresponding medical instrument products, marking the detection item data which do not meet the preset data requirement as detection difference values compared with deviation values which correspond to the preset data requirement, comparing the detection difference values with corresponding preset detection difference threshold values, marking the detection items which do not meet the preset data requirement as overstock items if the detection difference values exceed the corresponding preset detection difference threshold values, weighting and summing the number of overstock items and the number of detection items which do not meet the preset data requirement to obtain product difference values, comparing the product difference values with preset product difference threshold values, marking the corresponding medical instrument products as high-deviation products if the product difference values exceed the preset product difference threshold values, and marking the corresponding medical instrument products as low-deviation products if the product difference values do not exceed the preset product difference threshold values.
Further, the specific analysis process of the supervision planning analysis is as follows:
setting a production supervision period with the number of days of P1, collecting the medical instrument production quantity and daily production quality coefficient of each processing day of a corresponding production line in the production supervision period when the number of production days reaches P1, and sequencing the processing days according to the numerical value of the daily production quality coefficient from large to small; acquiring processing days at the front T1 and processing days at the rear T1, marking the processing days as analysis days, wherein T1 is less than P1/3, establishing an effective mass set for the production quantity of the medical instrument at all the analysis days, performing variance calculation on the effective mass set to obtain a daily yield difference coefficient, and performing numerical comparison on the daily yield difference coefficient and a preset daily yield difference coefficient threshold;
if the daily yield difference coefficient does not exceed the preset daily yield difference coefficient threshold value, judging that the adverse effect of the production efficiency on the product quality is small, and marking the range consisting of the maximum value and the minimum value of the production quantity of the medical instrument in the processing day in the production supervision period as a preferable yield range; if the daily yield difference coefficient exceeds the preset daily quality difference coefficient threshold value, judging that the production efficiency has great adverse effect on the product quality, and marking a range consisting of the average value and the minimum value of the production amounts of the medical devices on the post-T1 processing day after sequencing as a preferable production range.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the equipment and the environment of the area where the corresponding analysis object i is located are effectively detected and analyzed through the process deviation supervision and analysis of the corresponding analysis object i, so that the inspection and maintenance of the corresponding equipment and the environment regulation and control of the corresponding area are timely carried out, the area where the corresponding analysis object i is located is monitored, the risk operation in the corresponding analysis object i is identified based on the monitoring image, the corresponding operation personnel are marked as the superior operation personnel, the good operation personnel or the inferior operation personnel through the analysis, the corresponding monitoring judgment symbol of the corresponding analysis object i is generated, and the personnel operation supervision and identification of each process are realized, so that the safety production of the medical instrument product is ensured, and the product quality and the production efficiency are improved; and the corresponding analysis object i is comprehensively judged and analyzed to generate a procedure supervision abnormal signal or a procedure supervision normal signal, the procedure abnormal condition analysis result is more accurate, corresponding management is timely and targeted to make corresponding improvement countermeasures, so that safe and efficient production of each procedure of a corresponding production line is effectively ensured, and the quality of the produced medical instrument product is improved;
2. According to the invention, the quality of the medical instrument products of the corresponding production line is detected, so that a production line processing disqualification signal or a production line processing qualification signal of the corresponding production line on the corresponding processing day is generated, and the production quality condition of the corresponding production line of a corresponding manager is reminded, so that the corresponding manager can timely make corresponding countermeasures to ensure the subsequent product processing quality; and the production efficiency is improved while the product quality of medical instruments produced by the corresponding production line is ensured, so that the intelligent degree is high.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
FIG. 1 is a system block diagram of a first embodiment of the present invention;
fig. 2 is a system block diagram of a second embodiment of the present invention.
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.
Embodiment one: as shown in fig. 1, the intelligent supervisory system for medical instrument production based on artificial intelligence provided by the invention comprises a server, a procedure deviation supervisory analysis module, a procedure monitoring, identifying and evaluating module and a procedure abnormality comprehensive judging module, wherein the server is in communication connection with the procedure deviation supervisory analysis module, the procedure monitoring, identifying and evaluating module and the procedure abnormality comprehensive judging module; the method comprises the steps that a server obtains a production line of corresponding medical equipment and all production procedures of the corresponding production line, the corresponding production procedures are marked as analysis objects i, i= {1,2, …, n }, n represents the number of the production procedures in the corresponding production line and n is a natural number larger than 1; the process deviation monitoring analysis module acquires environment deviation data and equipment operation data corresponding to the analysis object i, and accordingly performs process deviation monitoring analysis, a deviation judgment symbol PL1 or PL2 of the analysis object i is generated through the process deviation monitoring analysis, the process deviation judgment symbol PL1 or PL2 of the analysis object i is sent to the process abnormality comprehensive judgment module through the server, effective detection and analysis of equipment of each process and the environment of the area are realized, and timely inspection and maintenance of corresponding equipment and environmental regulation of corresponding areas are facilitated, so that the high-efficiency production of medical instrument products is ensured, and meanwhile, the product quality is ensured; the specific analysis process of the process deviation supervision analysis is as follows:
The method comprises the steps that environment deviation data of an analysis object i are obtained, the environment deviation data comprise environment temperature deviation values, environment humidity deviation values, environment wind power deviation values and environment dust deviation values of an area where the analysis object i is located, wherein the environment temperature deviation values, the environment humidity deviation values, the environment wind power deviation values and the environment dust deviation values are data values representing the deviation degree of the temperature of a corresponding area compared with the preset proper temperature, the larger the values of the environment temperature deviation values are, the more difficult the real-time temperature of the corresponding area is to be in favor of the stable and smooth process of the medical instrument production process, the more difficult the quality of the produced product is to be improved, and the larger the values of the environment humidity deviation values, the environment wind power deviation values and the environment dust deviation values are, namely the larger the values of the environment wind power deviation values are, the more difficult the real-time environment of the corresponding area is to be in favor of the production and processing of the medical instrument product;
respectively carrying out numerical comparison on the environmental temperature deviation value, the environmental humidity deviation value, the environmental wind deviation value and the environmental dust deviation value with corresponding preset thresholds, and if at least one of the environmental temperature deviation value, the environmental humidity deviation value, the environmental wind deviation value and the environmental dust deviation value exceeds the corresponding preset thresholds, indicating that the environmental condition of the area where the corresponding analysis object i is located is poor, generating a deviation judgment symbol PL1; if the environmental temperature deviation value, the environmental humidity deviation value, the environmental wind deviation value and the environmental dust deviation value do not exceed the corresponding preset thresholds, carrying out normalization calculation on the environmental temperature deviation value HQi, the environmental humidity deviation value HGi, the environmental wind deviation value HFi and the environmental dust deviation value HSi through a regional normalization analysis formula CPi=a1× HQi +a2×HGi+a3×HFi+a4×HSi to obtain an initial deviation analysis coefficient CPi; wherein a1, a2, a3 and a4 are preset weight coefficients, a4 is more than a1 and a2 is more than a3 and more than 0;
The numerical value of the initial deviation analysis coefficient CPi is in a direct proportion relation with the environmental temperature deviation value HQi, the environmental humidity deviation value HGi, the environmental wind deviation value HFi and the environmental dust deviation value HSi, and the larger the numerical value of the initial deviation analysis coefficient CPi is, the more unsuitable the production of medical instrument products is for the environmental condition of the area where the corresponding analysis object i is located; comparing the initial bias analysis coefficient CPi of the analysis object i with a preset initial bias analysis coefficient threshold value in a numerical mode; if the initial bias analysis coefficient CPi exceeds a preset initial bias analysis coefficient threshold value, indicating that the environmental condition of the area where the corresponding analysis object i is located is poor, generating a deviation judgment symbol PL1; if the initial bias analysis coefficient CPi does not exceed the preset initial bias analysis coefficient threshold value, indicating that the environmental condition of the area where the corresponding analysis object i is located is good, acquiring the equipment operation data of the analysis object i;
the equipment operation data comprise noise coefficients and vibration coefficients generated in the operation process of the production equipment corresponding to the analysis object i; the noise coefficient is a data value representing the magnitude of a noise decibel value generated in the production process of corresponding production equipment, and the larger the generated noise decibel value is, the larger the value of the corresponding noise coefficient is, so that the abnormal operation of the equipment is indicated; the vibration coefficient is a data magnitude which represents the sum of the vibration frequency and the vibration amplitude in the production process of corresponding production equipment, and the larger the vibration amplitude and the vibration frequency of the equipment, the larger the value of the corresponding vibration coefficient is, so that the abnormal operation of the equipment is indicated;
If at least one of the noise coefficient and the vibration coefficient exceeds a corresponding preset threshold value, indicating that the equipment corresponding to the analysis object i runs poorly, generating a deviation judging symbol PL1, if the noise coefficient and the vibration coefficient do not exceed the corresponding preset threshold value, respectively marking a difference value of the noise coefficient compared with the corresponding preset threshold value and a difference value of the vibration coefficient compared with the corresponding preset threshold value as a sound threshold difference value coefficient and a vibration threshold difference value coefficient, and carrying out numerical calculation on the sound threshold difference value coefficient QYi and the vibration threshold difference value coefficient ZYi through a formula SYi=b1× QYi +b2× ZYi to obtain an equipment evaluation coefficient SYi; wherein b1 and b2 are preset weight coefficients, and b2 is more than b1 and more than 0;
moreover, the numerical value of the equipment evaluation coefficient SYi is in a direct proportion relation with the tone threshold difference coefficient QYi and the vibration threshold difference coefficient ZYi, and the larger the numerical value of the equipment evaluation coefficient SYi is, the better the equipment operation corresponding to the analysis object i is; and carrying out numerical comparison on the equipment evaluation coefficient and a preset equipment evaluation coefficient threshold value, if the equipment evaluation coefficient does not exceed the preset equipment evaluation coefficient threshold value, generating a deviation judgment symbol PL1, and if the equipment evaluation coefficient does not exceed the preset equipment evaluation coefficient threshold value, indicating that the equipment corresponding to the analysis object i operates better, generating a deviation judgment symbol PL2.
The process monitoring, identifying and evaluating module monitors the area where the corresponding analysis object i is located, and identifies risk operation in the corresponding analysis object i based on the monitoring image, so that the corresponding operator is marked as a top-grade operator, a good-grade operator or a bad-grade operator through analysis, a monitoring judgment symbol JK1 or JK2 corresponding to the analysis object i is generated through analysis, the monitoring judgment symbol JK1 or JK2 is sent to the process anomaly comprehensive judgment module through a server, personnel operation supervision and identification of each process are realized, inspection guidance of the corresponding process or post adjustment training of the corresponding operator is facilitated in time, and therefore the product quality and the production efficiency are improved while the safe production of medical instrument products is ensured; the specific operation process of the process monitoring, identifying and evaluating module is as follows:
monitoring the area where the corresponding analysis object i is located through a monitoring camera, acquiring the action behaviors of operators in the area where the analysis object i is located through a monitoring image, identifying the action behaviors of the operators to mark action behaviors which do not meet the requirements of corresponding procedures, marking the action behaviors which do not meet the requirements of the corresponding procedures as risk operations, and acquiring the operation category to which the corresponding risk operations belong and the operation risk coefficient of the corresponding operation category; the values of the operation risk coefficients are all larger than zero, and the operation risk coefficients are recorded in advance by corresponding management staff and stored in a server, if the potential safety hazard degree of the corresponding operation class is larger, the operation risk coefficient of the corresponding operation class is larger;
Multiplying the risk operation quantity of the corresponding operation class of the corresponding operator with the corresponding operation risk coefficient to obtain an action judgment value, and carrying out summation calculation on the action judgment values of all operation classes of the corresponding operator to obtain an action re-analysis value; it should be noted that, the larger the numerical value of the action re-analysis value is, the greater the operation risk degree of the corresponding operator is; comparing the action re-analysis value with a preset action re-analysis value range in a numerical value mode, judging that the operation of a corresponding operator is very irregular and marked as a inferior operator if the action re-analysis value exceeds the maximum value of the preset action re-analysis value range, judging that the operation of the corresponding operator is good and marked as a good operator if the action re-analysis value is within the preset action re-analysis value range, and judging that the operation of the corresponding operator is excellent and marked as a superior operator if the action re-analysis value does not exceed the minimum value of the preset action re-analysis value range; if a bad operator exists in the area where the analysis object i is located, indicating that the production risk of the analysis object i is large, generating a monitoring judgment symbol JK1;
if no inferior operators exist in the area where the analysis object i is located, calculating the ratio of the number of the superior operators to obtain a monitoring identification coefficient, wherein the larger the numerical value of the monitoring identification coefficient is, the larger the production and processing risk corresponding to the analysis object i is; the monitoring identification coefficient is compared with a preset monitoring identification coefficient threshold value in a numerical mode, if the monitoring identification coefficient exceeds the preset monitoring identification coefficient threshold value, a monitoring judgment symbol JK1 is generated, if the monitoring identification coefficient does not exceed the preset monitoring identification coefficient threshold value, a monitoring judgment symbol JK2 is generated, and if the monitoring identification coefficient does not exceed the preset monitoring identification coefficient threshold value, the production risk of the analysis object i is smaller; moreover, corresponding management personnel can timely strengthen supervision and subsequent training education of inferior personnel as required, so that production safety is guaranteed.
The process anomaly comprehensive judgment module carries out comprehensive judgment and analysis on the corresponding analysis object i, generates a process supervision abnormal signal or a process supervision normal signal through comprehensive judgment and analysis, realizes comprehensive analysis and evaluation of the corresponding analysis object i, has more accurate process anomaly analysis results, and enables corresponding management personnel to timely and pertinently carry out corresponding improvement countermeasures, thereby effectively ensuring safe and efficient production of each process of a corresponding production line, improving the quality of produced medical instrument products, and transmitting the process supervision abnormal signal or the process supervision normal signal to a background supervision terminal through a server; the specific operation process is as follows:
acquiring a process deviation judgment symbol PL1 or PL2 and a monitoring judgment symbol JK1 or JK2 corresponding to the analysis object i, and generating a process supervision abnormal signal corresponding to the analysis object i if PL1 n JK1, PL1 n JK2 or PL2 n JK1 are acquired; if PL2 n JK2 is acquired, acquiring wastewater production data, exhaust gas production data, and waste material production data corresponding to the analysis object i, and performing numerical calculation on the wastewater production data HLi, the exhaust gas production data QLi, and the waste material production data PLi by the formula GYi =tu1× HLi +tu2× QLi +tu3×pli to obtain a process anomaly value GYi; wherein, tu1, tu2 and tu3 are preset weight coefficients, the values of tu1, tu2 and tu3 are all larger than 1, and tu3 is larger than tu1 and larger than tu2; as can be seen from the above, the magnitude of the process anomaly value GYi is in direct proportion to the wastewater production amount data HLi, the exhaust gas production amount data QLi, and the waste material production amount data PLi;
Calculating the ratio of the abnormal process value GYi to the medical instrument processing efficiency value corresponding to the analysis object i to obtain a process representation value GBi, wherein the medical instrument processing efficiency value is a data value representing the amount of the corresponding medical instrument production in unit time, and the larger the numerical value of the medical instrument processing efficiency value is, the more the corresponding medical instrument production in unit time is; the larger the numerical value of the process expression value GBi is, the worse the production performance of the corresponding analysis object i is; and comparing the process representation value GBi with a corresponding preset process representation threshold value, generating a process supervision abnormal signal if the process representation value GBi exceeds the preset process representation threshold value, and generating a process supervision normal signal corresponding to the analysis object i if the process representation value GBi does not exceed the preset process representation threshold value.
Further, if the process supervision abnormal signal is generated, the corresponding analysis object i is marked as a non-standard process, if the process supervision normal signal is generated, the corresponding analysis object i is marked as a standard process, and the ratio of the number of the non-standard processes to the number of the standard processes in the corresponding production line is calculated to obtain a production supervision coefficient; and (3) carrying out numerical comparison on the production supervision coefficient and a preset production supervision coefficient threshold value, if the production supervision coefficient exceeds the preset production supervision coefficient threshold value, indicating that the production potential safety hazard of the corresponding production line is extremely large, generating a comprehensive maintenance and adjustment signal of the corresponding production line, sending the comprehensive maintenance and adjustment signal to a background supervision terminal through a server, and after receiving the comprehensive maintenance and adjustment signal, the corresponding manager should pause the operation of the corresponding production line in time, and carrying out equipment inspection and maintenance of the production line, corresponding personnel training and environment regulation, thereby reducing the production potential safety hazard of the production line.
Embodiment two: as shown in fig. 2, the difference between the present embodiment and embodiment 1 is that the server is in communication connection with a product quality detection and summary module, wherein the product quality detection and summary module performs quality detection on the medical device products of the corresponding production line, marks the products with all detected item data reaching the preset data requirement as flawless products, and marks the corresponding medical device products as high-deviation products or low-deviation products through product difference analysis if the detected item data not reaching the preset data requirement exists in the corresponding medical device products; the method comprises the following steps: the method comprises the steps of collecting the number of detection items which do not meet the preset data requirements in corresponding medical equipment products, marking the detection item data which do not meet the preset data requirements as detection difference values compared with deviation values which correspond to the preset data requirements, carrying out numerical comparison on the detection difference values and corresponding preset detection difference threshold values, and marking the detection items which do not meet the preset data requirements as overstocked items if the detection difference values exceed the corresponding preset detection difference threshold values and indicate that the deviation of the corresponding detection items is extremely large;
the method comprises the steps of carrying out weighted summation calculation on the number CX of the overstocked items and the number JX of the detection items which do not reach the preset data requirement through a formula CY= (pe 1 CX+pe2 JX)/2 to obtain a product difference value CY; wherein, pe1 and pe2 are preset weight coefficients, and pe1 > pe2 > 0; and, the larger the value of the product difference value CY, the worse the quality of the corresponding medical instrument product is indicated; the product difference value CY is compared with a preset product difference threshold value in a numerical mode, if the product difference value CY exceeds the preset product difference threshold value, the corresponding medical instrument product is marked as a high-deviation product, and if the product difference value CY does not exceed the preset product difference threshold value, the corresponding medical instrument product is marked as a low-deviation product;
Carrying out numerical calculation on the number of flawless products, the number of high-deviation products and the number of low-deviation products in the corresponding production line per day to obtain daily product quality coefficients of the corresponding processing days of the production line; and (3) carrying out numerical comparison on the daily product quality coefficient and a preset daily quality coefficient, if the daily product quality coefficient exceeds a preset daily product quality coefficient threshold value, generating a production line processing disqualification signal, if the daily product quality coefficient does not exceed the preset daily product quality coefficient threshold value, generating a production line processing qualification signal, and sending the production line processing disqualification signal or the production line processing qualification signal of the corresponding production line to a background supervision terminal through a server so as to remind corresponding management personnel of the production quality condition of the corresponding production line, so that the corresponding management personnel can timely make corresponding countermeasures to ensure the subsequent product processing quality.
Embodiment III: as shown in fig. 2, the difference between the present embodiment and embodiments 1 and 2 is that the server is in communication connection with the production efficiency scientific planning module, the product quality detection summary module sends the daily product quality coefficient of the corresponding processing day of the corresponding production line to the production efficiency scientific planning module through the server, the production efficiency scientific planning module monitors and plans the processing efficiency of the corresponding production line, and analyzes to determine the preferred yield range of the corresponding production line, and sends the preferred yield range to the background monitoring terminal through the server, so that the scientific planning of the daily processing efficiency of the subsequent corresponding production line is realized, the production efficiency is improved while the product quality of the medical apparatus produced by the corresponding production line is ensured, and the intelligent degree is high; the specific analysis process is as follows:
Setting the production supervision period of P1 as days, wherein preferably, P1 is fifteen days; when the production days reach P1, acquiring the production quantity and daily production quality coefficient of the medical equipment of each processing day in the production supervision period of the corresponding production line, and sequencing the processing days according to the numerical value of the daily production quality coefficient from large to small; acquiring processing days at the front T1 and processing days at the rear T1, marking the processing days as analysis days, establishing an effective mass set for the medical instrument production quantity at all the analysis days, and performing variance calculation on the effective mass set to obtain daily yield difference coefficients, wherein the smaller the numerical value of the daily yield difference coefficients is, the smaller the product production efficiency state difference at all the analysis days is, and comparing the daily yield difference coefficients with a preset daily yield difference coefficient threshold value;
if the daily yield difference coefficient does not exceed the preset daily yield difference coefficient threshold value, judging that the production efficiency has small influence on the product quality, wherein the possibility of product quality problems caused by personnel operation and equipment conditions is high, and the processing production efficiency in the current production supervision period is in a normal state, marking the range consisting of the maximum value and the minimum value of the production quantity of the medical instrument in the processing day in the production supervision period as a preferred yield range, and subsequently strengthening personnel equipment supervision and operation training of each process;
If the daily yield difference coefficient exceeds a preset daily quality difference coefficient threshold value, judging that the production efficiency (namely daily yield) has great influence on the product quality, marking the processing daily at the rear T1 after sequencing as a target day, obtaining the minimum value of the medical instrument yield at the target day, carrying out summation calculation on the medical instrument yields at all the target days, taking an average value, and marking a range consisting of the average value and the minimum value of the medical instrument yields at the rear T1 processing day as a preferred yield range; the subsequent single-day production of the corresponding production line is carried out according to the preferred production range, so that the scientific planning of the subsequent production of medical instruments of the corresponding production line is realized.
The working principle of the invention is as follows: when the method is used, environmental deviation data and equipment operation data of a corresponding analysis object i are obtained through a process deviation supervision analysis module, process deviation supervision analysis is carried out according to the environmental deviation data and the equipment operation data, corresponding deviation judgment symbols of the analysis object i are generated, effective detection and analysis of equipment and the environments of the areas where the equipment are located in each process are realized, inspection and maintenance of the corresponding equipment and environment regulation of the corresponding areas are facilitated in time, a process monitoring, identifying and evaluating module monitors the areas where the corresponding analysis object i is located, risk operation in the corresponding analysis object i is identified based on a monitoring image, corresponding operators are marked as superior operators, good-grade operators or inferior-grade operators according to the monitoring, and corresponding monitoring judgment symbols of the corresponding analysis object i are generated through analysis, so that personnel operation supervision and identification of each process are realized, and the product quality and the production efficiency are improved while the safe production of medical instrument products is ensured; and the corresponding analysis object i is comprehensively judged and analyzed through the process anomaly comprehensive judgment module so as to generate a process supervision abnormal signal or a process supervision normal signal, the process anomaly analysis result is more accurate, corresponding management personnel can timely and pertinently make corresponding improvement countermeasures, thereby effectively ensuring the safe and efficient production of each process of the corresponding production line and improving the quality of the produced medical instrument products.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation. The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (8)
1. The intelligent supervisory system for the production of the medical equipment based on the artificial intelligence is characterized by comprising a server, a procedure deviation supervisory analysis module, a procedure monitoring, identifying and evaluating module and a procedure abnormality comprehensive judging module; the method comprises the steps that a server obtains a production line of corresponding medical equipment and all production procedures of the corresponding production line, the corresponding production procedures are marked as analysis objects i, i= {1,2, …, n }, n represents the number of the production procedures in the corresponding production line and n is a natural number larger than 1; the process deviation supervision and analysis module acquires environment deviation data and equipment operation data corresponding to the analysis object i, performs process deviation supervision and analysis according to the environment deviation data and the equipment operation data, generates a deviation judgment symbol PL1 or PL2 of the analysis object i through the process deviation supervision and analysis, and sends the process deviation judgment symbol PL1 or PL2 to the process abnormality comprehensive judgment module through the server;
The process monitoring, identifying and evaluating module monitors the area where the corresponding analysis object i is located, identifies risk operation in the corresponding analysis object i based on the monitoring image, marks the corresponding operator as a top-grade operator, a good-grade operator or a bad-grade operator according to the risk operation in the corresponding analysis object i through analysis, generates a monitoring judgment symbol JK1 or JK2 of the corresponding analysis object i through analysis, and sends the monitoring judgment symbol JK1 or JK2 to the process anomaly comprehensive judgment module through a server; the process anomaly comprehensive judgment module carries out comprehensive judgment and analysis on the corresponding analysis object i, generates a process supervision abnormal signal or a process supervision normal signal through comprehensive judgment and analysis, and sends the process supervision abnormal signal or the process supervision normal signal to the background supervision terminal through the server.
2. The intelligent supervisory system for manufacturing medical devices based on artificial intelligence according to claim 1, wherein the specific analysis process of the process deviation supervisory analysis comprises:
acquiring environment deviation data of an analysis object i, wherein the environment deviation data comprise an environment temperature deviation value, an environment humidity deviation value, an environment wind power deviation value and an environment dust deviation value of an area where the analysis object i is positioned, generating a deviation judgment symbol PL1 if at least one of the environment temperature deviation value, the environment humidity deviation value, the environment wind power deviation value and the environment dust deviation value exceeds a corresponding preset threshold value, and carrying out normalization calculation on the environment temperature deviation value, the environment humidity deviation value, the environment wind power deviation value and the environment dust deviation value to obtain a primary deviation analysis coefficient if the environment temperature deviation value, the environment humidity deviation value, the environment wind power deviation value and the environment dust deviation value do not exceed the corresponding preset threshold value;
If the initial bias analysis coefficient exceeds a preset initial bias analysis coefficient threshold value, generating a deviation judgment symbol PL1; if the initial deviation analysis coefficient does not exceed the preset initial deviation analysis coefficient threshold value, acquiring equipment operation data of the analysis object i, wherein the equipment operation data comprises a noise coefficient and a vibration coefficient generated in the operation process of production equipment corresponding to the analysis object i; if at least one of the noise coefficient and the vibration coefficient exceeds the corresponding preset threshold value, a deviation judging symbol PL1 is generated, if the noise coefficient and the vibration coefficient do not exceed the corresponding preset threshold value, a difference value of the noise coefficient compared with the corresponding preset threshold value and a difference value of the vibration coefficient compared with the corresponding preset threshold value are marked as a sound threshold difference value coefficient and a vibration threshold difference value coefficient respectively, the sound threshold difference value coefficient and the vibration threshold difference value coefficient are subjected to numerical calculation to obtain a device evaluation coefficient, if the device evaluation coefficient does not exceed the preset device evaluation coefficient threshold value, the deviation judging symbol PL1 is generated, and if the device evaluation coefficient does not exceed the preset device evaluation coefficient threshold value, the deviation judging symbol PL2 is generated.
3. The intelligent supervisory system for manufacturing medical devices based on artificial intelligence according to claim 1, wherein the specific operation process of the process monitoring, identifying and evaluating module comprises:
Monitoring the region where the corresponding analysis object i is located through a monitoring camera, acquiring the action behaviors of operators in the region where the analysis object i is located through a monitoring image, identifying the action behaviors of the corresponding operators to mark action behaviors which do not meet the requirements of corresponding procedures, marking the action behaviors which do not meet the requirements of the corresponding procedures as risk operations, acquiring the operation types to which the corresponding risk operations belong and the operation risk coefficients of the corresponding operation types, multiplying the risk operation quantity of the corresponding operation types of the corresponding operators by the corresponding operation risk coefficients to obtain action judgment values, and summing the action judgment values of all the operation types of the corresponding operators to obtain action re-analysis values;
if the action re-analysis value exceeds the maximum value of the preset action re-analysis value range, judging that the operation of the corresponding operator is very irregular and marking the operation as a bad operator, if the action re-analysis value is within the preset action re-analysis value range, judging that the operation of the corresponding operator is good and marking the operation as a good operator, and if the action re-analysis value does not exceed the minimum value of the preset action re-analysis value range, judging that the operation of the corresponding operator is excellent and marking the operation as a good operator; if the area where the analysis object i is located has inferior operators, generating a monitoring judgment symbol JK1; if no inferior operators exist in the area where the analysis object i is located, the number of the superior operators and the number of the superior operators are subjected to ratio calculation to obtain a monitoring identification coefficient, the monitoring identification coefficient is subjected to numerical comparison with a preset monitoring identification coefficient threshold value, a monitoring judgment symbol JK1 is generated if the monitoring identification coefficient exceeds the preset monitoring identification coefficient threshold value, and a monitoring judgment symbol JK2 is generated if the monitoring identification coefficient does not exceed the preset monitoring identification coefficient threshold value.
4. The intelligent supervisory system for medical equipment production based on artificial intelligence according to claim 1, wherein the specific operation procedure of the process anomaly comprehensive judgment module comprises:
acquiring a process deviation judgment symbol PL1 or PL2 and a monitoring judgment symbol JK1 or JK2 corresponding to the analysis object i, and generating a process supervision abnormal signal corresponding to the analysis object i if PL1 n JK1, PL1 n JK2 or PL2 n JK1 are acquired; if PL 2U JK2 is obtained, acquiring wastewater generation amount data, waste gas generation amount data and waste material generation amount data corresponding to the analysis object i, carrying out numerical calculation on the wastewater generation amount data, the waste gas generation amount data and the waste material generation amount data to obtain a process abnormal value, carrying out ratio calculation on the process abnormal value and a medical instrument processing efficiency value corresponding to the analysis object i to obtain a process representation value, generating a process supervision abnormal signal if the process representation value exceeds a preset process representation threshold value, and otherwise generating a process supervision normal signal corresponding to the analysis object i.
5. The intelligent supervisory system for medical equipment production based on artificial intelligence according to claim 4, wherein if a process supervision abnormal signal is generated, the corresponding analysis object i is marked as an nonstandard process, if a process supervision normal signal is generated, the corresponding analysis object i is marked as a standard process, and the ratio of the number of nonstandard processes to the number of standard processes in the corresponding production line is calculated to obtain a production supervision coefficient; if the production supervision coefficient exceeds a preset production supervision coefficient threshold, generating a comprehensive maintenance and adjustment signal corresponding to the production line, and sending the comprehensive maintenance and adjustment signal to a background supervision terminal through a server.
6. The intelligent supervisory system for medical equipment production based on artificial intelligence according to claim 1, wherein the server is in communication connection with both the product quality detection summarizing module and the production efficiency scientific planning module, wherein the product quality detection summarizing module performs quality detection on medical equipment products of a corresponding production line, marks products with all detection item data reaching preset data requirements as flawless products, and marks the corresponding medical equipment products as high-deviation products or low-deviation products through product difference analysis if the detection item data not reaching the preset data requirements exist in the corresponding medical equipment products;
carrying out numerical calculation on the number of flawless products, the number of high-deviation products and the number of low-deviation products in the corresponding production line per day to obtain daily product quality coefficients of the corresponding processing days of the production line; if the daily product quality coefficient exceeds a preset daily product quality coefficient threshold value, generating a production line processing disqualification signal, otherwise, generating a production line processing qualification signal, and transmitting the production line processing disqualification signal or the production line processing qualification signal of the corresponding production line to a background supervision terminal through a server; the production efficiency scientific planning module carries out supervision planning analysis on the processing efficiency of the corresponding production line, determines the preferred yield range of the corresponding production line through analysis, and sends the preferred yield range to the background supervision terminal through the server.
7. The intelligent supervisory system for medical device production based on artificial intelligence according to claim 6, wherein the specific analysis process of the product variance analysis is as follows:
the method comprises the steps of collecting the number of detection items which do not meet the preset data requirement in corresponding medical instrument products, marking the detection item data which do not meet the preset data requirement as detection difference values compared with deviation values which correspond to the preset data requirement, marking the detection items which do not meet the preset data requirement as overstock items if the detection difference values exceed corresponding preset detection difference thresholds, carrying out weighted summation calculation on the number of overstock items and the number of detection items which do not meet the preset data requirement to obtain product difference values, marking the corresponding medical instrument products as high-deviation products if the product difference values exceed preset product difference thresholds, and marking the corresponding medical instrument products as low-deviation products if the product difference values do not exceed the preset product difference thresholds.
8. The intelligent supervisory system for medical device production based on artificial intelligence according to claim 6, wherein the specific analysis process of the supervisory planning analysis is as follows:
Setting a production supervision period with the number of days of P1, collecting the medical instrument production quantity and daily production quality coefficient of each processing day of a corresponding production line in the production supervision period when the number of production days reaches P1, and sequencing the processing days according to the numerical value of the daily production quality coefficient from large to small; acquiring processing days at the front T1 and processing days at the rear T1, marking the processing days as analysis days, wherein T1 is less than P1/3, establishing an effective mass set for the medical instrument production capacity at all the analysis days, and performing variance calculation on the effective mass set to obtain daily yield difference coefficients;
if the daily yield difference coefficient does not exceed the preset daily yield difference coefficient threshold value, judging that the adverse effect of the production efficiency on the product quality is small, and marking the range consisting of the maximum value and the minimum value of the production quantity of the medical instrument in the processing day in the production supervision period as a preferable yield range; if the daily yield difference coefficient exceeds the preset daily quality difference coefficient threshold value, judging that the production efficiency has great adverse effect on the product quality, and marking a range consisting of the average value and the minimum value of the production amounts of the medical devices on the post-T1 processing day after sequencing as a preferable production range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310804673.1A CN117391427A (en) | 2023-07-03 | 2023-07-03 | Medical instrument production intelligent supervision system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310804673.1A CN117391427A (en) | 2023-07-03 | 2023-07-03 | Medical instrument production intelligent supervision system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117391427A true CN117391427A (en) | 2024-01-12 |
Family
ID=89470841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310804673.1A Pending CN117391427A (en) | 2023-07-03 | 2023-07-03 | Medical instrument production intelligent supervision system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117391427A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117670578A (en) * | 2024-02-02 | 2024-03-08 | 山东新时代药业有限公司 | Method for supervising production of granule based on information automation |
| CN117852972A (en) * | 2024-02-01 | 2024-04-09 | 宝应县鑫龙铸造有限公司 | Casting quality control system and method based on casting process monitoring data |
| CN117873009A (en) * | 2024-03-13 | 2024-04-12 | 山东鲁玻玻璃科技有限公司 | Monitoring system based on glass production process |
-
2023
- 2023-07-03 CN CN202310804673.1A patent/CN117391427A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117852972A (en) * | 2024-02-01 | 2024-04-09 | 宝应县鑫龙铸造有限公司 | Casting quality control system and method based on casting process monitoring data |
| CN117670578A (en) * | 2024-02-02 | 2024-03-08 | 山东新时代药业有限公司 | Method for supervising production of granule based on information automation |
| CN117670578B (en) * | 2024-02-02 | 2024-05-10 | 山东新时代药业有限公司 | Method for supervising production of granule based on information automation |
| CN117873009A (en) * | 2024-03-13 | 2024-04-12 | 山东鲁玻玻璃科技有限公司 | Monitoring system based on glass production process |
| CN117873009B (en) * | 2024-03-13 | 2024-05-24 | 山东鲁玻玻璃科技有限公司 | Monitoring system based on glass production process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117391427A (en) | Medical instrument production intelligent supervision system based on artificial intelligence | |
| CN108038553A (en) | Milling equipment state on_line monitoring and diagnostic system and monitoring, diagnosing method | |
| CN107038453A (en) | The fault early warning system and determination methods of a kind of Wind turbines | |
| CN116660672B (en) | Power grid equipment fault diagnosis method and system based on big data | |
| CN116360367A (en) | Industrial equipment Internet of things data acquisition method and system | |
| CN113177646B (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN117075528B (en) | Mobile phone accessory rotating assembly line monitoring system based on data processing | |
| CN117250208A (en) | Machine vision-based nano-imprint wafer defect accurate detection system and method | |
| CN117314244B (en) | Process flow data supervision system and method based on data analysis | |
| CN116153480A (en) | Intelligent information diagnosis and treatment system and method based on mobile medical equipment | |
| CN117032415A (en) | Equipment data supervision system and method based on temperature change | |
| CN117544998B (en) | Wireless network speed intelligent evaluation system based on artificial intelligence | |
| CN116028887A (en) | Analysis method of continuous industrial production data | |
| CN117350525A (en) | Crop growth data management decision-making system based on artificial intelligence | |
| CN116563050B (en) | Farmland soil heavy metal pollution analysis early warning method and early warning system | |
| CN116560946A (en) | Soil pollution data pushing system based on cloud computing | |
| CN116668256B (en) | Real-time operation influence early warning control system suitable for communication equipment | |
| CN116302763B (en) | Touch detection method and system for Micro LED display screen | |
| CN116955574B (en) | Intelligent customer service robot based on artificial intelligence and application method thereof | |
| CN117476040B (en) | Audio identification method and identification system | |
| CN117746345B (en) | Material state monitoring system and method based on big data | |
| CN117784668A (en) | Flour production line processing safety intelligent supervision system based on data analysis | |
| CN117176466B (en) | Information communication technology safety monitoring system and monitoring method thereof | |
| CN118095916A (en) | LED display screen module debugging system based on artificial intelligence | |
| CN117548911A (en) | Connector welding intelligent supervision system based on artificial intelligence |
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 |