CN117808238A - Delivery risk assessment system and method based on cloud computing - Google Patents

Abstract

The invention relates to the technical field of engineering evaluation, in particular to a delivery risk evaluation system and method based on cloud computing, comprising the following steps: the system comprises a state identification module, a fault evaluation module, a cloud analysis module, a risk correction module and an efficiency adjustment module, wherein the state identification module is used for identifying and recording the working state of equipment, the fault evaluation module is used for analyzing the relation between the running speed and the fault delay time, the cloud analysis module is used for predicting the preset construction period of a production project, the risk correction module is used for evaluating the risk of on-schedule delivery of the project, and the efficiency adjustment module is used for adjusting the speed of the equipment and giving a delay scheme.

Description

Delivery risk assessment system and method based on cloud computing

Technical Field

The invention relates to the technical field of engineering evaluation, in particular to a delivery risk evaluation system and method based on cloud computing.

Background

Project Management (PM) is a discipline for starting, planning, executing, managing and implementing projects, which can improve the efficiency of enterprises in conducting production activities and can be continuously expanded in project practice. Project management theory has been discussed and practiced well over the years to help teams deal with more complex problems in diverse environments. Assessment of construction period and risk calculation are important problems in the field of project management, and long-term, the work is completed by an experienced project manager.

However, with the advent of the automation age, most industries, particularly heavy industries such as petroleum, chemical engineering and the like, mostly adopt an automatic production line for production. In an automated project, the working efficiency and the failure risk of production equipment become decisive factors for whether the project can be delivered on schedule, but there are many factors influencing the working efficiency of the equipment, and these factors are different from one another for different equipment in different environments, so it is difficult for project managers as management personnel to comprehensively and accurately evaluate the construction period of an automated production line.

In addition, since the failure risk of the equipment is in positive correlation with the running speed of the equipment, even if a project manager can evaluate the construction period of an automatic production line, the failure risk of the equipment cannot be judged while the running speed of the equipment is improved, so that the delivery risk of different delivery dates is difficult to give.

Disclosure of Invention

The invention aims to provide a delivery risk assessment system and method based on cloud computing, which are used for solving the problems in the background technology.

In order to solve the technical problems, the invention provides the following technical scheme: a cloud computing-based delivery risk assessment system, comprising: the system comprises a state identification module, a fault evaluation module, a cloud analysis module, a risk correction module and an efficiency adjustment module;

the state identification module is used for identifying and recording the working state of the equipment according to the running speed of the production line and uploading the data to the cloud;

the fault evaluation module is used for acquiring fault records of the equipment and analyzing the relation between the running speed of the equipment and the fault delay time length by combining the fault conditions of the similar equipment;

the cloud analysis module is used for acquiring influence factors in the project execution process from the cloud, carrying out correlation calculation on various influence factors and the running speed of the equipment to obtain influence coefficients of the factors on the running speed, acquiring data from different channels, predicting the change function of the influence factors in the future, calculating the running speed of the equipment in the future, and further obtaining the preset construction period of the production project by combining fault risks;

the risk correction module is used for comparing the predicted running speed value with the actual measured value in the production process, calculating the accurate probability of the predicted construction period according to the deviation function of the predicted running speed value and the actual measured value, evaluating the risk of on-schedule delivery of the project according to the accurate probability, and sending data to a user;

and the efficiency adjusting module is used for calculating an adjusting value of the equipment speed according to a preset construction period when the project risk is higher than a threshold value, improving the production speed of the production line, limiting the increase of the fault risk, maximizing the possibility of on-schedule delivery of the equipment, and giving a delay scheme when the equipment cannot be delivered.

Further, the state recognition module includes: the production line detection unit and the fault identification unit;

the production line detection unit is used for detecting the running speed of the production line and obtaining the running speed of each device;

the fault identification unit is used for identifying and recording fault conditions of each device.

Further, the fault evaluation module includes: a record acquisition unit and a fault fitting unit;

the record acquisition unit is used for acquiring the historical operation speed, fault record, maintenance duration of the equipment and the fault probability of the similar equipment;

the fault fitting unit is used for fitting the relation between the equipment fault risk and the running speed, and further obtaining the relation between the construction period and the running speed.

Further, the cloud analysis module includes: the system comprises a correlation calculation unit, a factor prediction unit and a construction period assessment unit;

the correlation calculation unit is used for calculating correlation coefficients of various influence factors and the running speed of the equipment from the cloud;

the factor prediction unit is used for acquiring data from different channels and predicting future change trend of various influencing factors;

the construction period assessment unit is used for predicting a future running speed function of the equipment according to the change trend and the correlation coefficient of all the influence factors, and further obtaining the preset construction period of the equipment.

Further, the risk correction module includes: the device comprises a deviation calculation unit, a likelihood probability unit and a risk assessment unit;

the deviation calculation unit is used for calculating a deviation function between the predicted running speed function and the actually measured running speed function at fixed time intervals;

the likelihood probability unit is used for evaluating the accuracy of the predicted construction period and calculating the accuracy probability of the predicted construction period;

the risk assessment unit is used for calculating the risk probability that the production line cannot be delivered on schedule according to the prediction period and the prediction accuracy probability.

Further, the efficiency adjustment module includes: setting changing unit and hysteresis period unit

The setting changing unit is used for adjusting the setting probability of the equipment according to the relation between the running speed of the equipment and the construction period when the delivery risk is higher than the threshold value, so that the construction period is minimized;

the hysteresis cycle unit is used for giving out schemes of delay delivery when the equipment cannot be delivered on schedule, and calculating risk coefficients of different schemes.

A cloud computing-based delivery risk assessment method, comprising the steps of:

s100, detecting the working state of production line equipment, and uploading state information of the equipment to a cloud;

s200, acquiring a fault record of the equipment from the cloud, and analyzing the relation between the running speed of the equipment and the fault delay time by combining the fault condition of the similar equipment;

s300, obtaining influence factors in the project execution process from the cloud, and carrying out correlation calculation on various influence factors and the running speed of equipment to obtain influence coefficients of the influence factors on the running speed;

s400, predicting the running speed of the equipment in the future according to the change of each influence factor in the future and the influence coefficient of each influence factor on the running speed of the equipment, combining the fault risk, further obtaining the preset construction period of the production project, analyzing the deviation between the predicted value and the actual measured value, calculating the prediction accuracy, and evaluating the project delivery risk;

s500, when the project risk is higher than a threshold value, giving out a scheme of delay delivery according to a preset construction period, calculating risk coefficients of different schemes, and adjusting the setting speed of equipment so as to shorten the construction period.

Further, step S100 includes:

step S101, detecting the running speed of the production line, thereby obtaining the working state of the production line equipment, wherein the working state comprises the following steps: setting a speed, an operation speed, fault records and fault maintenance duration;

step S102, uploading working state data of the equipment to a cloud, and enabling the running speed of the equipment in the historical data to correspond to time one by one to obtain a function F (t) of the current equipment historical running speed changing along with time.

Further, step S200 includes:

step S200 includes:

step S201, acquiring the running speed, fault record and fault maintenance duration of production line equipment, and recording the total number of faults as m and the time when the faults occur as ti, wherein i= {1,2, …, m };

acquiring test data of a manufacturer of the equipment when the equipment leaves a factory through a cloud network, and acquiring a relation function A (x) between the running speed and the failure rate of the equipment when the equipment is tested, wherein x is the running speed of the equipment;

let x=f (ti), substituting the function a (x) to obtain the standard failure rate ai of the device at the running speed F (ti);

s202, evaluating a relation function between fault risks and operation speeds according to a standard fault rate and a history record:

wherein Q (F) is the probability of failure when the running speed of the current equipment is F, F represents the running speed of the equipment, b represents the times that the running speed of the equipment is less than F when the equipment fails, F (ti) represents the instant running speed of the equipment when the ith failure occurs in the history, m is the total times of failure, and the parameters are all greater than 0;

step S203, further calculating a relation function T1 (F) of the fault delay time length of the current equipment and the running speed of the equipment according to the data obtained in the step S202:

where hi represents the length of time for maintenance at the ith failure.

Further, step S300 includes:

step S300 includes:

s301, acquiring a change record of influence factors in the project history operation process according to records of various departments and sensors in a factory building, wherein the influence factors comprise: ambient temperature, ambient humidity, number of maintenance personnel, power supply current magnitude and continuous operating duration of the device;

after data of the equipment in a historical operation process are obtained, the historical data and the historical time are in one-to-one correspondence to obtain a function of each influence factor along with time, a function curve of the environmental temperature and the time is recorded as Y1 (t), a function of the environmental humidity and the time is recorded as Y2 (t), a function of the number of maintenance personnel and the time is recorded as Y3 (t), a function of the power supply current and the time is recorded as Y4 (t), and a function of the accumulated working time length and the time of the equipment is recorded as Y5 (t);

step S302, randomly sampling the value of each influence factor for n times in the historical time of the operation of the current equipment, wherein the sampling time point is recorded as tj, and j= {1,2, …, n };

the correlation coefficient between each influencing factor and the running speed of the equipment is calculated according to the following formula:

wherein rc represents a correlation coefficient between a c-th influence factor and an operation speed, yc (t) represents a change function of each influence factor with time, c= {1,2,3,4,5}, and-1 is not less than rc is not less than 1;

when the expression under the score line is 0, the value of rc is fixed to 0.

According to the invention, in the working process of an automation project, the historical working record of the equipment is analyzed, the change curve of the running speed of the equipment along with time is fitted, and the correlation coefficient of the factors and the historical construction period is evaluated according to the curves of weather, the number of maintenance personnel, electric power, temperature, set speed and the like in the same time, so that the sensitivity of different equipment to each influence factor in the current environment is effectively evaluated.

Further, step S400 includes:

step S400 includes:

s401, acquiring a function Z1 (t) of future environmental temperature and a function Z2 (t) of future environmental humidity over time from a meteorological department, acquiring a function Z3 (t) of future maintenance personnel number over time from a management department, acquiring a function Z4 (t) of power supply current value over time from an energy department, acquiring a function Z5 (t) of accumulated working time length of equipment over time from a production department, wherein the definition domain of the functions is (t 0, t0+b), t0 is a current time point, and b is a preset time length;

s402, predicting the running speed of the equipment in the future according to the prediction function and the correlation coefficient:

wherein F1 (t) represents an operation speed prediction function of the device, F0 represents a set speed of the device, and Zc (t) represents a prediction function of a c-th influence factor;

s403, marking the total production task as G, and calculating the construction period of the automatic production line by combining the fault condition through the following equation:

wherein T0 represents the current time, T represents the time when the task is completed, and T1 () is a function of the relationship between the fault delay time and the running speed of the device determined in step S203;

solving the equation to obtain the value of T, namely the estimated construction period when the automatic production line completes the task;

s404, when the automatic production line runs continuously, the running speed of equipment is collected once every time s, wherein s is a system preset value, and the prediction accuracy is calculated according to the following formula:

wherein D represents root mean square error of predicted value, v represents sampling times, F1 (t0+k.s) represents a kth sampling time, F2 (k.s) represents a predicted value of running speed of the current equipment, F2 (k.s) represents a measured value of running speed of the current equipment at the kth sampling time, and k represents a number of samples;

step S405, recording the scheduled delivery time as T2, and calculating the delivery probability in the scheduled time by means of a probability density function of normal distribution due to the fact that the error values of the predicted result and the actual measurement result approximately accord with the normal distribution:

wherein D is root mean square error of the predicted value, f (T2) is delivery probability in preset time, and e is the base of natural logarithm;

the delivery risk l=1-f (T2) and the system reports the delivery risk to the user in real time.

According to the method, the running speed of the automatic project can be predicted according to future environmental changes, and the predicted construction period of the project is obtained by combining the fault risk and the maintenance duration. According to the deviation function of the actual measurement result and the prediction result, the accurate probability of prediction is dynamically estimated, the estimated data is corrected, and the risk probability that the engineering cannot be delivered on schedule is further given, so that the comprehensive and effective risk estimation of the automatic production line is realized.

Further, step S500 includes:

step S501, when the delivery risk is greater than a set threshold value, giving an alarm to a user, and after the user inputs delay time T3, giving delivery risk L1 delayed to the moment T3, wherein the L1 is calculated according to a formula in the step S405 after T3 is replaced by T2 in the step S405;

and S502, when the user does not accept the delay scheme, calculating the value of F0 when T takes the minimum value in the step S400, marking the value as F2, and adjusting the set speed of the equipment from F0 to F2 so as to shorten the construction period of the automatic production line.

According to the method and the device for controlling the project delivery risk, when the project is at the delivery risk, the setting speed of the automatic equipment can be adjusted according to the relation between the equipment operation speed and the project period, so that the project period is shortened, the delivery risk is lower than a threshold value, the improvement of the production efficiency of an automatic production line by enterprises is facilitated, the project period is shortened, and the risk that the project cannot be delivered on schedule is reduced.

Compared with the prior art, the invention has the following beneficial effects:

1. according to the invention, in the working process of an automation project, the historical working record of the equipment is analyzed, the change curve of the running speed of the equipment along with time is fitted, and the correlation coefficient of the factors and the historical construction period is evaluated according to the curves of weather, the number of maintenance personnel, electric power, temperature, the setting speed and the like in the same time, so that the sensitivity of different equipment to each influence factor in the current environment is effectively evaluated, the problem that the working efficiency of the equipment is difficult to quantify is solved, the digitization degree of an automation production line is improved, and the manager is assisted in adjusting the running environment of the equipment.

2. According to the method, the running speed of the automatic project can be predicted according to future environmental changes, and the predicted construction period of the project is obtained by combining the fault risk and the maintenance duration. According to the deviation function of the actual measurement result and the prediction result, the accurate probability of prediction is dynamically estimated, the estimated data is corrected, and the risk probability that the engineering cannot be delivered on schedule is further given, so that the comprehensive and effective risk estimation of the automatic production line is realized.

3. According to the method and the device, the relation between the equipment fault risk and the running speed can be estimated according to the historical running speed, fault record and maintenance duration of the equipment and the fault probability of the similar equipment, the relation between the project and the running speed is further obtained, when the project has delivery risk, the setting speed of the automatic equipment is adjusted according to the relation between the equipment running speed and the project, so that the project is shortened, the delivery risk is lower than a threshold value, the production efficiency of an automatic production line is improved by enterprises, the project is shortened, and the risk that the project cannot be delivered on schedule is reduced.

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 cloud computing-based delivery risk assessment system of the present invention;

FIG. 2 is a schematic diagram of steps of a delivery risk assessment method based on cloud computing according to 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.

Referring to fig. 1, the present invention provides the following technical solutions: a cloud computing-based delivery risk assessment system, comprising: the system comprises a state identification module, a fault evaluation module, a cloud analysis module, a risk correction module and an efficiency adjustment module;

the state identification module is used for identifying and recording the working state of the equipment according to the running speed of the production line and uploading the data to the cloud;

the state identification module comprises: the production line detection unit and the fault identification unit;

the production line detection unit is used for detecting the running speed of the production line and obtaining the running speed of each device;

the fault identification unit is used for identifying and recording fault conditions of each device.

The fault evaluation module is used for acquiring fault records of the equipment and analyzing the relation between the running speed of the equipment and the fault delay time length by combining the fault conditions of the similar equipment;

the fault assessment module includes: a record acquisition unit and a fault fitting unit;

the record acquisition unit is used for acquiring the historical operation speed, fault record, maintenance duration of the equipment and the fault probability of the similar equipment;

the fault fitting unit is used for fitting the relation between the equipment fault risk and the running speed, and further obtaining the relation between the construction period and the running speed.

The cloud analysis module is used for acquiring influence factors in the project execution process from the cloud, carrying out correlation calculation on various influence factors and the running speed of the equipment to obtain influence coefficients of the factors on the running speed, acquiring data from different channels, predicting the change function of the influence factors in the future, calculating the running speed of the equipment in the future, and further obtaining the preset construction period of the production project by combining fault risks;

the cloud analysis module comprises: the system comprises a correlation calculation unit, a factor prediction unit and a construction period assessment unit;

the correlation calculation unit is used for calculating correlation coefficients of various influence factors and the running speed of the equipment from the cloud;

the factor prediction unit is used for acquiring data from different channels and predicting future change trend of various influencing factors;

the construction period assessment unit is used for predicting a future running speed function of the equipment according to the change trend and the correlation coefficient of all the influence factors, and further obtaining the preset construction period of the equipment.

The risk correction module is used for comparing the predicted running speed value with the actual measured value in the production process, calculating the accurate probability of the predicted construction period according to the deviation function of the predicted running speed value and the actual measured value, evaluating the risk of on-schedule delivery of the project according to the accurate probability, and sending data to a user;

the risk correction module includes: the device comprises a deviation calculation unit, a likelihood probability unit and a risk assessment unit;

the deviation calculation unit is used for calculating a deviation function between the predicted running speed function and the actually measured running speed function at fixed time intervals;

the likelihood probability unit is used for evaluating the accuracy of the predicted construction period and calculating the accuracy probability of the predicted construction period;

the risk assessment unit is used for calculating the risk probability that the production line cannot be delivered on schedule according to the prediction period and the prediction accuracy probability.

And the efficiency adjusting module is used for calculating an adjusting value of the equipment speed according to a preset construction period when the project risk is higher than a threshold value, improving the production speed of the production line, limiting the increase of the fault risk, maximizing the possibility of on-schedule delivery of the equipment, and giving a delay scheme when the equipment cannot be delivered.

The efficiency adjustment module includes: setting changing unit and hysteresis period unit

The setting changing unit is used for adjusting the setting probability of the equipment according to the relation between the running speed of the equipment and the construction period when the delivery risk is higher than the threshold value, so that the construction period is minimized;

the hysteresis cycle unit is used for giving out schemes of delay delivery when the equipment cannot be delivered on schedule, and calculating risk coefficients of different schemes.

As shown in fig. 2, a delivery risk assessment method based on cloud computing includes the following steps:

s100, detecting the working state of production line equipment, and uploading state information of the equipment to a cloud;

the step S100 includes:

step S101, detecting the running speed of the production line, thereby obtaining the working state of production line equipment, wherein the working state comprises the following steps: setting a speed, an operation speed, fault records and fault maintenance duration;

step S102, uploading working state data of the equipment to a cloud, and fitting a function F (t) of the running speed of the equipment, which changes along with time, in the cloud.

S200, acquiring a fault record of the equipment from the cloud, and analyzing the relation between the running speed of the equipment and the fault delay time by combining the fault condition of the similar equipment;

step S200 includes:

step S201, acquiring the running speed, fault record and fault maintenance duration of production line equipment, and recording the total number of faults as m and the time when the faults occur as ti, wherein i= {1,2, …, m };

acquiring test data of a manufacturer of the equipment when the equipment leaves a factory through a cloud network, and acquiring a relation function A (x) between the running speed and the failure rate of the equipment when the equipment is tested, wherein x is the running speed of the equipment;

let x=f (ti), substituting the function a (x) to obtain the standard failure rate ai of the device at the running speed F (ti);

s202, evaluating a relation function between fault risks and operation speeds according to a standard fault rate and a history record:

wherein Q (F) is the probability of failure when the running speed of the current equipment is F, F represents the running speed of the equipment, b represents the times that the running speed of the equipment is less than F when the equipment fails, F (ti) represents the instant running speed of the equipment when the ith failure occurs in the history, m is the total times of failure, and the parameters are all greater than 0;

step S203, further calculating a relation function T1 (F) of the fault delay time length of the current equipment and the running speed of the equipment according to the data obtained in the step S202:

where hi represents the length of time for maintenance at the ith failure.

S300, obtaining influence factors in the project execution process from the cloud, and carrying out correlation calculation on various influence factors and the running speed of equipment to obtain influence coefficients of the factors on the running speed;

step S300 includes:

s301, obtaining influence factors in the project operation process according to the history record and sensors in the factory building, wherein the influence factors comprise: ambient temperature, ambient humidity, number of maintenance personnel, power supply current magnitude and continuous operating duration of the device;

fitting out a change function of each influence factor along with time, marking a function curve of the ambient temperature and the time as Y1 (t), marking an ambient humidity function as Y2 (t), marking a number function of maintenance personnel as Y3 (t), marking a function of the power supply current as Y4 (t), and marking a function of the continuous working time length of the equipment as Y5 (t);

s302, randomly sampling the total running time of equipment in a history record for n times, wherein the sampling time point is recorded as tj, and j= {1,2, …, n };

the correlation coefficient between each influencing factor and the running speed of the equipment is calculated according to the following formula:

wherein rc represents a correlation coefficient between a c-th influence factor and an operation speed, yc (t) represents a change function of each influence factor with time, c= {1,2,3,4,5}, and-1 is not less than rc is not less than 1;

when the expression under the score line is 0, the value of rc is fixed to 0.

S400, calculating the running speed of the equipment in the future, combining the fault risk, further obtaining the preset construction period of the production project, analyzing the deviation between the predicted value and the measured value, calculating the prediction accuracy, and evaluating the project delivery risk;

step S400 includes:

s401, acquiring a function Z1 (t) of future environmental temperature and a function Z2 (t) of future environmental humidity over time from a meteorological department, acquiring a function Z3 (t) of future maintenance personnel number over time from a management department, acquiring a function Z4 (t) of power supply current value over time from an energy department, acquiring a function Z5 (t) of accumulated working time length of equipment over time from a production department, wherein the definition domain of the functions is (t 0, t0+b), t0 is a current time point, and b is a preset time length;

s402, predicting the running speed of the equipment in the future according to the prediction function and the correlation coefficient:

wherein F1 (t) represents an operation speed prediction function of the device, F0 represents a set speed of the device, and Zc (t) represents a prediction function of a c-th influence factor;

s403, marking the total production task as G, and calculating the construction period of the automatic production line by combining the fault condition through the following equation:

wherein T0 represents the current time, T represents the time when the task is completed, and T1 () is a function of the relationship between the fault delay time and the running speed of the device determined in step S203;

solving the equation to obtain the value of T, namely the estimated construction period when the automatic production line completes the task;

s404, when the automatic production line runs continuously, the running speed of equipment is collected once every time s, wherein s is a system preset value, and the prediction accuracy is calculated according to the following formula:

wherein D represents root mean square error of predicted value, v represents sampling times, F1 (t0+k.s) represents a kth sampling time, F2 (k.s) represents a predicted value of running speed of the current equipment, F2 (k.s) represents a measured value of running speed of the current equipment at the kth sampling time, and k represents a number of samples;

step S405, recording the scheduled delivery time as T2, and calculating the delivery probability in the scheduled time by means of a probability density function of normal distribution due to the fact that the error values of the predicted result and the actual measurement result approximately accord with the normal distribution:

wherein D is root mean square error of the predicted value, f (T2) is delivery probability in preset time, and e is the base of natural logarithm;

the delivery risk l=1-f (T2) and the system reports the delivery risk to the user in real time.

S500, when the project risk is higher than a threshold value, giving out a scheme of delay delivery according to a preset construction period, calculating risk coefficients of different schemes, and adjusting the setting speed of equipment so as to shorten the construction period.

Step S500 includes:

step S501, when the delivery risk is greater than a set threshold value, giving an alarm to a user, and after the user inputs delay time T3, giving delivery risk L1 delayed to the moment T3, wherein the L1 is calculated according to a formula in the step S405 after T3 is replaced by T2 in the step S405;

and S502, when the user does not accept the delay scheme, calculating the value of F0 when T takes the minimum value in the step S400, marking the value as F2, and adjusting the set speed of the equipment from F0 to F2 so as to shorten the construction period of the automatic production line.

Examples:

the user starts the system, obtains the running speed, fault record and fault maintenance duration record of the production line equipment, fits the function F (t) of the running speed of the equipment along with the time change in the cloud, sets F (t) =10+t, obtains the function and the correlation coefficient of each influence factor, and obtains: the correlation coefficient with the ambient temperature is 0.1, the correlation coefficient with the ambient humidity is-0.3, the correlation coefficient with the number of maintenance personnel is 0.2, the correlation coefficient with the magnitude of the power supply current is 0.4, the correlation coefficient with the continuous working time of the equipment is 0.8, the set speed of the equipment is 20m/min, and after the predicted value of each factor is obtained, the running speed prediction function F1 (t) =20+0.1Z1 (t) -0.3Z2 (t) +0.2Z3 (t) +0.4Z4 (t) +0.8Z5 (t) is calculated.

Setting the time points of the faults to be 2, 4, 6 and 8 when the faults occur for 4 times, wherein when the faults occur, the instantaneous speeds of the equipment are respectively 12cm/min, 14cm/min, 16cm/min and 18cm/min, and the fault risks of the equipment of the same type under the speeds are respectively: 20%, 40%, 60% and 80%, F1 (t) =15 cm/min, the calculated risk of failure q=50%, further obtaining a delay time of 20min;

according toThe resulting delivery risk was 73%.

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 (10)

1. A cloud computing-based delivery risk assessment method, the method comprising the steps of:

s100, detecting the working state of production line equipment, and uploading state information of the equipment to a cloud;

s200, acquiring a fault record of the equipment from the cloud, and analyzing the relation between the running speed of the equipment and the fault delay time by combining the fault condition of the similar equipment;

s300, obtaining influence factors in the project execution process from the cloud, and carrying out correlation calculation on various influence factors and the running speed of equipment to obtain influence coefficients of the influence factors on the running speed;

s400, predicting the running speed of the equipment in the future according to the change of each influence factor in the future and the influence coefficient of each influence factor on the running speed of the equipment, combining the fault risk, further obtaining the preset construction period of the production project, analyzing the deviation between the predicted value and the actual measured value, calculating the prediction accuracy, and evaluating the project delivery risk;

s500, when the project risk is higher than a threshold value, giving out a scheme of delay delivery according to a preset construction period, calculating risk coefficients of different schemes, and adjusting the setting speed of equipment so as to shorten the construction period.

2. The cloud computing-based delivery risk assessment method of claim 1, wherein:

the step S100 includes:

step S101, detecting the running speed of the production line, thereby obtaining the working state of production line equipment, wherein the working state comprises the following steps: setting a speed, an operation speed, fault records and fault maintenance duration;

step S102, uploading working state data of the equipment to a cloud, and enabling the running speed of the equipment in the historical data to correspond to time one by one to obtain a function F (t) of the current equipment historical running speed changing along with time;

step S200 includes:

step S201, acquiring the running speed, fault record and fault maintenance duration of production line equipment, and recording the total number of faults as m and the time when the faults occur as ti, wherein i= {1,2, …, m };

acquiring test data of a manufacturer of the equipment when the equipment leaves a factory through a cloud network, and acquiring a relation function A (x) between the running speed and the failure rate of the equipment when the equipment is tested, wherein x is the running speed of the equipment;

let x=f (ti), substituting the function a (x) to obtain the standard failure rate ai of the device at the running speed F (ti);

s202, evaluating a relation function between fault risks and operation speeds according to a standard fault rate and a history record:

wherein Q (F) is the probability of failure when the running speed of the current equipment is F, F represents the running speed of the equipment, b represents the times that the running speed of the equipment is less than F when the equipment fails, F (ti) represents the instant running speed of the equipment when the ith failure occurs in the history, m is the total times of failure, and the parameters are all greater than 0;

step S203, further calculating a relation function T1 (F) of the fault delay time length of the current equipment and the running speed of the equipment according to the data obtained in the step S202:

where hi represents the length of time for maintenance at the ith failure.

3. The cloud computing-based delivery risk assessment method of claim 1, wherein:

step S300 includes:

s301, acquiring a change record of influence factors in the project history operation process according to records of various departments and sensors in a factory building, wherein the influence factors comprise: ambient temperature, ambient humidity, number of maintenance personnel, power supply current magnitude and continuous operating duration of the device;

after data of the equipment in a historical operation process are obtained, the historical data and the historical time are in one-to-one correspondence to obtain a function of each influence factor along with time, a function curve of the environmental temperature and the time is recorded as Y1 (t), a function of the environmental humidity and the time is recorded as Y2 (t), a function of the number of maintenance personnel and the time is recorded as Y3 (t), a function of the power supply current and the time is recorded as Y4 (t), and a function of the accumulated working time length and the time of the equipment is recorded as Y5 (t);

step S302, randomly sampling the value of each influence factor for n times in the historical time of the operation of the current equipment, wherein the sampling time point is recorded as tj, and j= {1,2, …, n };

the correlation coefficient between each influencing factor and the running speed of the equipment is calculated according to the following formula:

wherein rc represents a correlation coefficient between a c-th influence factor and an operation speed, yc (t) represents a change function of each influence factor with time, c= {1,2,3,4,5}, and-1 is not less than rc is not less than 1;

when the expression under the score line is 0, the value of rc is fixed to 0.

4. The cloud computing-based delivery risk assessment method of claim 1, wherein:

step S400 includes:

s401, acquiring a function Z1 (t) of future environmental temperature and a function Z2 (t) of future environmental humidity over time from a meteorological department, acquiring a function Z3 (t) of future maintenance personnel number over time from a management department, acquiring a function Z4 (t) of power supply current value over time from an energy department, acquiring a function Z5 (t) of accumulated working time length of equipment over time from a production department, wherein the definition domain of the functions is (t 0, t0+b), t0 is a current time point, and b is a preset time length;

s402, predicting the running speed of the equipment in the future according to the prediction function and the correlation coefficient:

wherein F1 (t) represents an operation speed prediction function of the device, F0 represents a set speed of the device, and Zc (t) represents a prediction function of a c-th influence factor;

s403, marking the total production task as G, and calculating the construction period of the automatic production line by combining the fault condition through the following equation:

wherein T0 represents the current time, T represents the time when the task is completed, and T1 () is a function of the relationship between the fault delay time and the running speed of the device determined in step S203;

solving the equation to obtain the value of T, namely the estimated construction period when the automatic production line completes the task;

s404, when the automatic production line runs continuously, the running speed of equipment is collected once every time s, wherein s is a system preset value, and the prediction accuracy is calculated according to the following formula:

wherein D represents root mean square error of predicted value, v represents sampling times, F1 (t0+k.s) represents a kth sampling time, F2 (k.s) represents a predicted value of running speed of the current equipment, F2 (k.s) represents a measured value of running speed of the current equipment at the kth sampling time, and k represents a number of samples;

step S405, recording the scheduled delivery time as T2, and calculating the delivery probability in the scheduled time by means of a probability density function of normal distribution due to the fact that the error values of the predicted result and the actual measurement result approximately accord with the normal distribution:

wherein D is root mean square error of the predicted value, f (T2) is delivery probability in preset time, and e is the base of natural logarithm;

the delivery risk l=1-f (T2) and the system reports the delivery risk to the user in real time.

5. The cloud computing-based delivery risk assessment method of claim 1, wherein:

step S500 includes:

step S501, when the delivery risk is greater than a set threshold value, giving an alarm to a user, and after the user inputs delay time T3, giving delivery risk L1 delayed to the moment T3, wherein the L1 is calculated according to a formula in the step S405 after T3 is replaced by T2 in the step S405;

and S502, when the user does not accept the delay scheme, calculating the value of F0 when T takes the minimum value in the step S400, marking the value as F2, and adjusting the set speed of the equipment from F0 to F2 so as to shorten the construction period of the automatic production line.

6. A cloud computing-based delivery risk assessment system, the system comprising the following modules: the system comprises a state identification module, a fault evaluation module, a cloud analysis module, a risk correction module and an efficiency adjustment module;

the state identification module is used for identifying and recording the working state of the equipment according to the running speed of the production line and uploading the data to the cloud;

the fault evaluation module is used for acquiring fault records of the equipment and analyzing the relation between the running speed of the equipment and the fault delay time length by combining the fault conditions of the similar equipment;

the cloud analysis module is used for acquiring influence factors in the project execution process from the cloud, carrying out correlation calculation on various influence factors and the running speed of the equipment to obtain influence coefficients of the factors on the running speed, acquiring data from different channels, predicting the change function of the influence factors in the future, calculating the running speed of the equipment in the future, and further obtaining the preset construction period of the production project by combining fault risks;

the risk correction module is used for comparing the predicted running speed value with the actual measured value in the production process, calculating the accurate probability of the predicted construction period according to the deviation function of the predicted running speed value and the actual measured value, evaluating the risk of on-schedule delivery of the project according to the accurate probability, and sending data to a user;

and the efficiency adjusting module is used for calculating an adjusting value of the equipment speed according to a preset construction period when the project risk is higher than a threshold value, improving the production speed of the production line, limiting the increase of the fault risk, maximizing the possibility of on-schedule delivery of the equipment, and giving a delay scheme when the equipment cannot be delivered.

7. The cloud computing based delivery risk assessment system of claim 6, wherein:

the state identification module comprises: the production line detection unit and the fault identification unit;

the production line detection unit is used for detecting the running speed of the production line and obtaining the running speed of each device;

the fault identification unit is used for identifying and recording fault conditions of each device;

the fault assessment module includes: a record acquisition unit and a fault fitting unit;

the record acquisition unit is used for acquiring the historical operation speed, fault record, maintenance duration of the equipment and the fault probability of the similar equipment;

the fault fitting unit is used for fitting the relation between the equipment fault risk and the running speed, and further obtaining the relation between the construction period and the running speed.

8. The cloud computing based delivery risk assessment system of claim 6, wherein:

the cloud analysis module comprises: the system comprises a correlation calculation unit, a factor prediction unit and a construction period assessment unit;

the correlation calculation unit is used for calculating correlation coefficients of various influence factors and the running speed of the equipment from the cloud;

the factor prediction unit is used for acquiring data from different channels and predicting future change trend of various influencing factors;

the construction period assessment unit is used for predicting a future running speed function of the equipment according to the change trend and the correlation coefficient of all the influence factors, and further obtaining the preset construction period of the equipment.

9. The cloud computing based delivery risk assessment system of claim 6, wherein:

the risk correction module includes: the device comprises a deviation calculation unit, a likelihood probability unit and a risk assessment unit;

the deviation calculation unit is used for calculating a deviation function between the predicted running speed function and the actually measured running speed function at fixed time intervals;

the likelihood probability unit is used for evaluating the accuracy of the predicted construction period and calculating the accuracy probability of the predicted construction period;

the risk assessment unit is used for calculating the risk probability that the production line cannot be delivered on schedule according to the prediction period and the prediction accuracy probability.

10. The cloud computing based delivery risk assessment system of claim 6, wherein:

the efficiency adjustment module includes: setting changing unit and hysteresis period unit

The setting changing unit is used for adjusting the setting probability of the equipment according to the relation between the running speed of the equipment and the construction period when the delivery risk is higher than the threshold value, so that the construction period is minimized;

the hysteresis cycle unit is used for giving out schemes of delay delivery when the equipment cannot be delivered on schedule, and calculating risk coefficients of different schemes.