CN114382490A - Shield tunneling machine cutter head wear assessment and prediction method - Google Patents
Shield tunneling machine cutter head wear assessment and prediction method Download PDFInfo
- Publication number
- CN114382490A CN114382490A CN202111670981.7A CN202111670981A CN114382490A CN 114382490 A CN114382490 A CN 114382490A CN 202111670981 A CN202111670981 A CN 202111670981A CN 114382490 A CN114382490 A CN 114382490A
- Authority
- CN
- China
- Prior art keywords
- data
- cutter
- wear
- cutter head
- sample set
- 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
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/003—Arrangement of measuring or indicating devices for use during driving of tunnels, e.g. for guiding machines
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/06—Making by using a driving shield, i.e. advanced by pushing means bearing against the already placed lining
- E21D9/08—Making by using a driving shield, i.e. advanced by pushing means bearing against the already placed lining with additional boring or cutting means other than the conventional cutting edge of the shield
Abstract
The invention belongs to the technical field of mechanical equipment maintenance, and discloses a shield tunneling machine cutter head wear assessment and prediction method, which comprises the following steps: acquiring Data of a Data sample set in a shield tunneling machine tunneling state; preprocessing the Data sample set Data to obtain a Data sample set Data 1; calculating equivalent wear W of cutter head of shield machine during cutter changing each timem(ii) a Computing coefficient vector q based on Lasso regressionL(ii) a Acquiring a Data sample set Data2 of the shield tunneling machine in a state of waiting tunneling; calculating the accumulated equivalent wear W of a cutter head of a rear shield tunneling machine for a tunneling mileage of L metersL(ii) a And obtaining an evaluation prediction result of the wear of the cutter head of the shield tunneling machine. The method adopts the Lasso regression to establish a prediction model, has the function of regularization sparse solution screening, and eliminates the characteristics with weak contribution degree to the prediction result in the input, thereby eliminating the multiple collinearity problem commonly existing in the linear regression model, and finallyThe characteristic subset used by the model is more accurate, the model prediction accuracy is higher, the generalization capability is stronger, and the evaluation and prediction of the whole abrasion loss of the cutter head are convenient.
Description
Technical Field
The invention belongs to the technical field of mechanical equipment maintenance, relates to a method for evaluating and predicting cutter head abrasion of a shield machine, in particular to a method for evaluating and predicting the cutter head abrasion of the shield machine based on Lasso regression, and can be used for evaluating and predicting the cutter head abrasion of the shield machine.
Background
At present, with the continuous acceleration of urbanization process in China, the development and utilization of urban underground space are developed rapidly. The shield method has become the main construction method of the current tunnel engineering due to the characteristics of safe construction technology, strong soil layer adaptability, small influence on the environment along the line and the like. The shield machine drives the cutter through the cutter head to break the rock, and carries the gravel, sand and soil into the soil bin through the screw machine, so that the tunnel is continuously tunneled underground. The cutter head system is a core component for realizing rock breaking and tunneling of the shield tunneling machine. Due to the complex and severe construction environment and the long-time working under the conditions of low speed, heavy load and dynamic variable working conditions, the excessive abrasion and abnormal damage of the cutter become the main reasons of the fault shutdown of the shield machine, and the method is also one of the main problems of the shield safe and efficient tunneling. In shield construction, once the cutter is excessively worn, if the cutter cannot be found and replaced in time, the wear rate of other cutters on the cutter head can be greatly accelerated. On the other hand, the cutter replacement process is complex, difficult and high in cost, and engineering accidents such as instability of an excavation face and tunnel collapse are easily caused by opening the bin and replacing the cutter. The problems of tool wear and the influence caused by the tool wear are more prominent in complex strata, the safety of life and property is threatened once the tool wear and damage are carelessly treated, and the high-frequency warehouse opening inspection of the tool is forced to avoid the problems. However, under the influence of the severe working environment of the shield machine and the complex mechanical structure of the cutter head system, the wear condition of the cutter is difficult to directly acquire, and the degradation state of the cutter head system cannot be sensed in real time in the actual construction process, so that the cutter changing time can be judged only by manual experience at present, or a regular warehouse opening cutter changing strategy is adopted, a large amount of omission or misjudgment is caused, and unnecessary risks and resource waste are caused. Particularly, under the complex geological conditions, such as environments of crossing the river, submarine tunnels and the like which cannot be opened frequently, the problem of cutter abrasion failure is more prominent, and once major accidents occur, the serious consequences that the whole shield machine is scrapped and the project is completely stopped are often caused.
At present, the method for evaluating the wear of the shield machine cutter mainly comprises wear mechanism research and sensor monitoring. The shield machine is a complex device of thermoelectric coupling, the cutter is used as a core component of the shield machine, the abrasion degradation correlation characteristic of the cutter is influenced by various factors, the number of parameters in the operation process of the shield machine is huge due to the complex operation condition of the shield machine, all the parameters cannot be considered in theoretical analysis, the establishment of an analysis model also usually depends on expert experience and stress analysis under an ideal state, the expert experience is summarized by a service expert in long-term shield practice, rigorous mathematical proofs do not exist, and the mechanism model has large sidedness due to the excessive assumption of stress analysis scenes, so the method is usually only suitable for qualitative analysis of specific operation conditions. For example, Wu Jun et al, 2017, 8 Yue, in an article of shield cutter wear mechanism and prediction analysis, volume 8, volume 30, No. 8, of the school of highways, analyze the shield cutter wear mechanism based on the metal tribology theory, consider the combined action of abrasive wear, adhesive wear and fatigue wear, combine Rabinowicz abrasive wear, Archard adhesive wear and fatigue wear calculation formulas, introduce a hob rock breaking mechanical model of university of Colorado mining and a cutter rock breaking mechanical model of university of China, and derive a universal calculation model for shield hob and cutter wear prediction. The method has the disadvantages that the specificity of shield machines of different types under different working conditions is not considered, and although the universal calculation model is widely applicable, the precision is not high. The wear evaluation based on the sensor obtains the wear information of the tool by direct measurement through installing a special sensor. According to the detection principle, the current detection methods can be divided into three types, namely electrical detection, hydraulic detection and gas detection. Liu Xiang Wei et al, 11 months in 2017, in an article of "research on ultrasonic-based shield cutter wear Wireless detection System" at No. 11, volume 37, in Tunnel construction (Chinese and English), studied the shield cutter wear detection technology by using 433MHz wireless data transmission technology on the basis of ultrasonic detection technology, and completed a real-time wear detection device. The method has the disadvantages that the sensor is not placed under a severe working condition for testing, and the precision of the sensor after being separated from the laboratory environment cannot be ensured.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) the existing scheme of judging the tool changing time by depending on manual experience or adopting a regular opening tool changing strategy can cause a great deal of omission or misjudgment, and unnecessary risks and resource waste are caused.
(2) The existing shield machine cutter abrasion evaluation method based on abrasion mechanism research cannot consider all parameters, and expert experience does not have rigorous mathematical verification and is only suitable for qualitative analysis of specific working condition conditions.
(3) The specificity of shield machines of different types under different working conditions is not considered in the existing method, and although the general calculation model is widely applicable, the accuracy is not high.
(4) In the existing sensor-based wear assessment method, the sensor is not placed under a severe working condition for testing, and the precision of the sensor after being separated from a laboratory environment cannot be guaranteed.
The difficulty in solving the above problems and defects is: the method is characterized in that the tool changing time is determined by the manual experience, the working experience of construction workers accumulated for years is mainly relied on, and a clear method cannot be formed and provided for newly added working workers; the simple mechanical mathematical relationship between factors influencing the abrasion of the cutter head of the shield tunneling machine and the abrasion of the cutter head of the shield tunneling machine cannot be established due to different cutter head materials of the shield tunneling machine, the abrasion degree under different working environments and the complex working environment.
The significance of solving the problems and the defects is as follows: the shield machine cutter head abrasion evaluation and prediction method can keep higher precision under different shield machine models and different working environments of the shield machine, can accurately help constructors to determine the replacement time of the shield machine cutter head, can ensure that the shield machine cutter head can be utilized to the maximum extent, can avoid unsafe accidents caused by too late cutter replacement time, and has very important significance in the working of the shield machine.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method for evaluating and predicting the cutter wear of a shield machine, in particular to a method for evaluating and predicting the cutter wear of the shield machine based on Lasso regression, aiming at solving the problems of narrow application range, poor accuracy and low reliability in the prior art.
The invention is realized in this way, a method for evaluating and predicting the cutter head wear of a shield machine comprises the following steps:
selecting a time point t with the last tool change number less than P from shield construction tool change recorded data0And the time point t when the number of tool changing is more than Q1The formed tool degradation interval [ t ]0,t1]H times of tool changing recording data in the system are carried out, wherein each time of tool changing recording data comprises 16 kinds of characteristic data of rock-soil bearing capacity characteristic data of a region to be constructed of the shield machine, shield machine tunneling control characteristic data acquired by a sensor in the shield machine construction process, shield machine PLC state characteristic data and shield machine tunneling mileage data; removing tool changing record Data which are less than or equal to 0 in total propelling force Data of shield tunneling machine excavation control Data and less than or equal to 0 in cutter head rotating speed Data in H times of tool changing records to form Data sample set Data in the shield tunneling machine excavation state;
comprehensively preprocessing the Data to obtain a Data sample set Data 1; calculating the equivalent abrasion loss of the cutter head when the shield machine changes the cutter every time, and taking the equivalent abrasion loss as a label; applying a multivariate linear regression model-Lasso regression model, performing parameter estimation by using the Lasso regression model, removing insignificant influence factors according to the value of the estimated parameter, and finally establishing a calculation formula of the equivalent wear loss of the cutter head; and (3) evaluating and predicting the wear degree of the cutter head by using a formula after calculating the equivalent wear of the cutter head at a certain distance.
Further, the method for evaluating and predicting the wear of the cutter head of the shield tunneling machine comprises the following steps:
acquiring a Data sample set Data in a shield tunneling machine tunneling state;
providing a sample set of raw data for model building
Step two, preprocessing a Data sample set Data;
removing abnormal values in the data sample set, normalizing the abnormal value processing result, and then performing noise reduction processing on the normalized result, thereby improving the quality of the data sample set and improving the accuracy of the model
Step three, calculating the equivalent wear W of the cutter head of the shield tunneling machine when the cutter head is changed each timem；
Providing labels for model training
Step four, calculating a coefficient vector q based on Lasso regressionL；
Calculating coefficient vectors, and eliminating the characteristics with small influence on the abrasion of the cutter head of the shield machine according to the values of the coefficient vectors
Step five, acquiring a Data sample set Data2 of the shield tunneling machine in a state of waiting tunneling;
obtaining a test set and testing the precision of the model; selecting the same data set when estimating the cutter head abrasion loss of the shield machine later
Sixthly, calculating the accumulated equivalent wear W of a cutter head of the shield tunneling machine after the tunneling mileage is L metersL；
Obtaining the accumulated equivalent wear W of the cutter head of the rear shield machine with the tunneling mileage of L metersL
And seventhly, obtaining an evaluation prediction result of the cutter head abrasion of the shield tunneling machine.
According to the evaluation and prediction result of the wear of the cutter head of the shield machine, a constructor can accurately determine the cutter changing time, so that the cutter head of the shield machine can be utilized to the maximum extent, and unsafe accidents caused by too late cutter changing time can be avoided.
Further, the acquiring of the Data sample set Data in the shield tunneling machine tunneling state in the step one includes:
(1) selecting a time point t with the last tool change number less than P from shield construction tool change recorded data0And the time point t when the number of tool changing is more than Q1The formed tool degradation interval [ t ]0,t1]The recorded data of H times of tool changing comprises the feature data of the rock-soil bearing capacity of the region to be constructed of the shield machine and the tunneling control feature of the shield machine collected by the sensor in the construction process of the shield machine16 kinds of characteristic data including data, shield tunneling machine PLC state characteristic data and shield tunneling machine excavation mileage data; the shield tunneling machine tunneling control data comprises the total propelling force of the shield tunneling machine and the cutter head rotating speed; the PLC state characteristic data of the shield machine comprises the propelling speed, the cutter torque, the penetration degree, the rotating speed of the screw machine, the rotating speed of the cutter, the pressure of a left lower soil bin, the pressure of a left middle soil bin, the pressure of a left upper soil bin, the propelling pressure of the group A, the propelling pressure of the group B, the propelling pressure of the group C and the propelling pressure of the group D, wherein P is less than or equal to 4, Q is more than or equal to 30, and H is more than or equal to 20.
(2) And removing the cutter changing record Data which are less than or equal to 0 in the total propelling force Data of the shield tunneling machine tunneling control Data and less than or equal to 0 in the cutter head rotating speed Data in the H cutter changing records, wherein the rest M cutter changing record Data form a Data sample set Data in the shield tunneling machine tunneling state.
The preprocessing of the Data sample set Data in the second step comprises:
abnormal value processing is carried out on each feature Data in the Data sample set Data, the abnormal value processing result is normalized, then noise reduction processing is carried out on the normalized result, and the preprocessed Data sample set Data1 is obtained;
the preprocessing of the Data sample set Data specifically comprises:
(1) replacing the value of 0 in each kind of characteristic Data contained in the Data sample set Data with 0.00000001 to obtain a Data sample set Data' for processing the abnormal value of the Data sample set Data;
(2) carrying out the most value normalization on each feature Data contained in the Data sample set Data 'by the following formula to obtain a Data sample set Data' after the most value normalization;
wherein z is*Represents the result of the most-valued normalization of each feature Data z in the Data sample set DatamaxAnd zminRespectively representing the maximum value and the minimum value of z;
(3) sampling each kind of characteristic Data contained in the Data sample set Data 'through a sliding window, calculating the root mean square value of the characteristic Data contained in the Data sample set Data' in each window, and using the calculation result as the substitute value of the characteristic Data contained in the Data sample set Data 'in the window to realize the noise reduction of each kind of characteristic Data of the Data'; wherein the data denoising comprises:
1) setting the length of the sliding window to m1Step length of window movement is s1(ii) a Wherein m is1In [30,60 ]]Within the interval, take any positive integer, s1Value of (a) and m1Equal;
2) the rms value of all data in the window after each sliding is calculated as follows:
wherein d isiRepresents the RMS value, y, of all data within the ith sliding windowaAnd a represents the a data of the data in the window after the i sliding, and sigma represents the summation operation.
The Data sample set Data is preprocessed to obtain a Data sample set Data 1.
Further, the equivalent wear W of the cutter head of the shield tunneling machine during cutter changing each time is calculated in the third stepmThe method comprises the following steps:
(1) acquiring the abrasion loss of each cutter when each cutter is changed:
1) setting a central area, a front area and an edge area of a cutter head of the shield tunneling machine to contain N cutters, wherein N is more than or equal to 46, judging whether each cutter is replaced during cutter changing each time according to the record of a cutter maintenance log, if so, the abrasion loss of the replaced cutter is 0, and if not, executing the step 2);
2) judging whether the abrasion loss of the tool which is not replaced is normal according to the abrasion record of the tool in the tool maintenance log, if so, executing the step 3); otherwise, taking the replacement threshold value of the tool which is not replaced and has abnormal wear loss as the wear loss of the tool when the tool is replaced each time; wherein, the replacement threshold value of the edge region cutter is 5mm, and the replacement threshold values of the front region cutter and the central region cutter are 15 mm;
3) judging whether the tool which is not replaced and has normal abrasion loss has an abrasion loss measured value, if so, taking the abrasion loss measured value as the abrasion loss of the tool during tool changing each time; otherwise, the interpolation result of the 2 times wear value of the tool in the tool maintenance log is used as the wear amount of the tool during each tool changing.
(2) Weighting and summing the abrasion loss of the cutter head N during cutter changing each time to obtain the equivalent abrasion loss W of the cutter head during the cutter changing for the mth timem：
Wherein α represents the wear coefficient of the tool, the wear coefficient of the tool in the center region and the front region is 1, the wear coefficient of the tool in the edge region is 3, and wmnShows the wear amount of the nth tool when the mth tool is changed.
Further, calculating the coefficient vector q based on Lasso regression in the fourth stepLThe method comprises the following steps:
calculating the equivalent wear W of the cutter head when the mth cutter changingmLogarithmic value y ofmAnd adopting a Lasso regression method to pass through the Data sample sets Data1 and WmLogarithmic value y ofmCalculating coefficient vector q of shield tunneling machine cutterhead accumulated equivalent wear loss logarithm value calculation formulaL：
ym＝lnWm；
Wherein q represents a regression coefficient vector, R16The expression regression coefficient vector q is a column vector containing 16 elements, 16 expression Data is 16 kinds of characteristic Data which influence the equivalent abrasion loss of a cutterhead and are contained in the Data sample set Data, sigma represents a summation operation, lambda represents an adjusting coefficient, and x representsmAnd the influence factor pair value vector represents the accumulated equivalent wear quantity of the cutter head during the m-th cutter changing.
The step five of acquiring the Data sample set Data2 of the shield tunneling machine in the state of waiting tunneling comprises the following steps:
screening out the characteristic Data of the equivalent wear extent of the cutter head which is finally influenced from the 16 characteristic Data of the equivalent wear extent of the cutter head which is contained in the Data sample set Data1 by adopting a Lasso regression regularization sparse screening method: cutter torque, rock soil bearing capacity, total propelling force, left lower soil bin pressure, screw machine rotating speed and tunneling mileage; assuming that the future tunneling mileage is L meters, the characteristic Data values of the cutterhead torque, the rock-soil bearing capacity, the total propelling force, the left lower soil bin pressure and the screw machine rotating speed are the same as the characteristic Data values recorded in the last tool changing of the Data sample set Data1, and a Data sample set Data2 of the shield tunneling machine in the state to be tunneled is formed.
Further, the cumulative equivalent wear W of the cutter head of the shield tunneling machine is calculated according to the tunneling mileage L meters in the sixth stepLThe method comprises the following steps:
(1) carrying out logarithmic calculation on each kind of characteristic Data of the equivalent wear loss of the cutter head, which are influenced by the Data sample set Data2 in the state of the shield tunneling machine to be tunneled, to obtain a Data sample set Data2 ', and calculating the logarithmic value y of the accumulated equivalent wear loss of the cutter head of the shield tunneling machine after the tunneling mileage is L meters through the Data sample set Data 2':
y＝qL(Data2′)+ε；
where ε represents the random error.
(2) Carrying out exponential calculation on a logarithmic value y of the accumulated equivalent wear loss of the cutter head of the rear shield machine with the tunneling mileage of L meters to obtain an accumulated equivalent wear loss W of the cutter head of the rear shield machine with the tunneling mileage of L metersL；
WL＝ey。
The seventh step of obtaining the evaluation prediction result of the wear of the cutter head of the shield tunneling machine comprises the following steps:
according to the wear grade interval determined in the actual construction process, checking the accumulated equivalent wear W of a cutter head of the shield tunneling machine after the tunneling mileage is L metersLAnd in the abrasion grade interval, evaluating the abrasion degree of a cutter head of the shield machine after the shield machine tunnels for L meters.
By combining all the technical schemes, the invention has the advantages and positive effects that: the method for evaluating and predicting the wear of the cutter head of the shield tunneling machine adopts an industrial big data driving method, can be used for evaluating and predicting the wear of the cutter head of the shield tunneling machine, solves the technical problem of narrow application range in the prior art, and simultaneously improves the accuracy of monitoring the health state of the cutter and predicting the service life of the cutter.
According to the method, geological characteristics and shield machine operation state characteristic data are fully considered, the cutter abrasion loss of different areas of the cutter head is weighted and summed to realize the evaluation and prediction of the overall abrasion state of the cutter head, and the method is not specific to a single cutter, more suitable for actual industrial scenes, wide in application range and high in accuracy.
According to the method, the cutter wear measurement record is taken as the basis, the equivalent overall wear value of the cutter is constructed by weighting and summing the single cutter wear amount in different areas of the cutter, and compared with the traditional research taking the single cutter wear amount as a prediction object, the method can more accurately establish the mapping relation between the observation data and the overall wear amount of the cutter, and is convenient for evaluating and predicting the overall wear amount of the cutter.
According to the method, the Lasso regression is adopted to establish the prediction model, the regularized sparse solution screening function is achieved, the features which have weak contribution degree to the prediction result in the input process can be eliminated, the multiple collinearity problem which generally exists in a linear regression model is eliminated, the feature subset used by the final model is more accurate, the model prediction accuracy is higher, and the generalization capability is stronger.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments of the present invention will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a shield tunneling machine cutterhead wear evaluation prediction method provided by an embodiment of the present invention.
Fig. 2 is a schematic diagram of a shield tunneling machine cutter head wear evaluation prediction method provided by an embodiment of the invention.
Fig. 3 is a diagram illustrating 448 future 5-ring cutter head wear increment predictions in an example validation provided by an embodiment of the invention.
Fig. 4 is a schematic diagram of the zone division of the cutter head of the shield tunneling machine provided by the embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a method for evaluating and predicting the cutter head wear of a shield tunneling machine, which is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, a method for evaluating and predicting wear of a cutter head of a shield tunneling machine according to an embodiment of the present invention includes the following steps:
s101, acquiring Data sample set Data in a shield tunneling machine tunneling state;
s102, preprocessing a Data sample set Data;
s103, calculating the equivalent wear W of the cutter head of the shield tunneling machine during cutter changing each timem；
S104, calculating a coefficient vector q based on Lasso regressionL；
S105, acquiring a Data sample set Data2 of the shield tunneling machine in a state of waiting tunneling;
s106, calculating the accumulated equivalent wear W of a cutter head of the shield tunneling machine after the tunneling mileage is L metersL；
And S107, obtaining an evaluation prediction result of the shield tunneling machine cutterhead abrasion.
A schematic diagram of a shield tunneling machine cutterhead wear assessment and prediction method provided by the embodiment of the invention is shown in fig. 2.
Fig. 4 is a schematic diagram of the zone division of the cutter head of the shield tunneling machine according to the embodiment of the invention.
The technical solution of the present invention is further described below with reference to specific examples.
The invention aims to solve the problems of poor accuracy and low reliability in the prior art, and provides a shield machine cutter head wear assessment and prediction method based on Lasso regression by adopting an industrial big data driving method.
The idea for realizing the aim of the invention is to select the time point t when the last time of tool changing is less than P from the recorded data of the shield construction tool changing0And the time point t when the number of tool changing is more than Q1The formed tool degradation interval [ t ]0,t1]And then, tool changing record Data which are less than or equal to 0 in the total propelling force Data of the shield tunneling machine propelling control Data and less than or equal to 0 in the cutter head rotating speed Data in the H-time tool changing record are eliminated, and Data sample set Data in the shield tunneling machine propelling state are formed. Then, the Data is subjected to comprehensive preprocessing, and a Data sample set Data1 is obtained. And then, calculating the equivalent abrasion loss of the cutter head when the shield machine changes the cutter every time, and taking the equivalent abrasion loss as a label. Then, a multiple linear regression model, the Lasso regression model, was applied. And (3) performing parameter estimation by using a Lasso regression model, removing insignificant influence factors according to the estimated parameter value, and finally establishing a calculation formula of the equivalent wear of the cutter head. By using the formula, after the equivalent wear of the cutterhead after a certain distance is calculated, the wear degree of the cutterhead is evaluated and predicted.
In order to achieve the purpose, the technical scheme adopted by the invention comprises the following steps:
(1) acquiring a Data sample set Data in a shield tunneling machine tunneling state:
(1a) selecting a time point t with the last tool change number less than P from shield construction tool change recorded data0And the time point t when the number of tool changing is more than Q1Formed byTool degradation interval [ t ]0,t1]H times of tool changing recording data in the system are carried out, wherein each time of tool changing recording data comprises 16 kinds of characteristic data of rock-soil bearing capacity characteristic data of a region to be constructed of the shield machine, shield machine tunneling control characteristic data acquired by a sensor in the shield machine construction process, shield machine PLC state characteristic data and shield machine tunneling mileage data; the shield tunneling machine tunneling control data comprises the total propelling force of the shield tunneling machine and the cutter head rotating speed; the shield tunneling machine PLC state characteristic data comprises a propelling speed, a cutter torque, a penetration degree, a screw machine rotating speed, a cutter rotating speed, a left lower soil bin pressure, a left middle soil bin pressure, a left upper soil bin pressure, an A group propelling pressure, a B group propelling pressure, a C group propelling pressure and a D group propelling pressure, P is less than or equal to 4, Q is more than or equal to 30, and H is more than or equal to 20;
(1b) removing tool changing record Data which are less than or equal to 0 in total propelling force Data of shield tunneling machine tunneling control Data and less than or equal to 0 in cutter head rotating speed Data in H times of tool changing records, wherein the rest M tool changing record Data form Data sample set Data in a shield tunneling machine tunneling state;
(2) preprocessing a Data sample set Data:
abnormal value processing is carried out on each feature Data in the Data sample set Data, the abnormal value processing result is normalized, and then noise reduction processing is carried out on the normalized result to obtain a preprocessed Data sample set Data 1;
(3) calculating equivalent wear W of cutter head of shield machine during cutter changing each timem：
(3a) Acquiring the abrasion loss of each cutter when each cutter is changed:
(3a1) setting a central area, a front area and an edge area of a cutter head of the shield tunneling machine to contain N cutters, wherein N is more than or equal to 46, judging whether each cutter is replaced during cutter changing each time according to the record of a cutter maintenance log, if so, the abrasion loss of the replaced cutter is 0, and if not, executing the step (3a 2);
(3a2) judging whether the abrasion loss of the tool which is not replaced is normal according to the abrasion record of the tool in the tool maintenance log, if so, executing a step (3a3), otherwise, taking the replacement threshold of the tool which is not replaced and has abnormal abrasion loss as the abrasion loss of the tool during each tool changing, wherein the replacement threshold of the tool in the edge area is 5mm, and the replacement thresholds of the tool in the front area and the tool in the central area are 15 mm;
(3a3) judging whether the tool which is normal in abrasion loss and is not replaced has an abrasion measured value, if so, taking the abrasion measured value as the abrasion loss of the tool during each tool changing, otherwise, taking an interpolation result of 2 times of abrasion values of the tool in a tool maintenance log as the abrasion loss of the tool during each tool changing;
(3b) weighting and summing the abrasion loss of the cutter head N during cutter changing each time to obtain the equivalent abrasion loss W of the cutter head during the cutter changing for the mth timem：
Wherein α represents the wear coefficient of the tool, the wear coefficient of the tool in the center region and the front region is 1, the wear coefficient of the tool in the edge region is 3, and wmnThe abrasion quantity of the nth cutter when the mth cutter is changed is shown;
(4) computing coefficient vector q based on Lasso regressionL：
Calculating the equivalent wear W of the cutter head when the mth cutter changingmLogarithmic value y ofmAnd adopting a Lasso regression method to pass through the Data sample sets Data1 and WmLogarithmic value y ofmCalculating coefficient vector q of shield tunneling machine cutterhead accumulated equivalent wear loss logarithm value calculation formulaL：
ym＝lnWm
Wherein q represents a regression coefficient vector, R16The expression regression coefficient vector q is a column vector containing 16 elements, 16 expression Data is 16 kinds of characteristic Data which influence the equivalent abrasion loss of a cutterhead and are contained in the Data sample set Data, sigma represents a summation operation, lambda represents an adjusting coefficient, and x representsmRepresenting the logarithm of the influence factors of the accumulated equivalent wear of the cutter head during the mth cutter changingA vector of values;
(5) acquiring a Data sample set Data2 of the shield tunneling machine in a state of waiting tunneling:
screening out the characteristic Data of the equivalent wear extent of the cutter head which is finally influenced from the 16 characteristic Data of the equivalent wear extent of the cutter head which is contained in the Data sample set Data1 by adopting a Lasso regression regularization sparse screening method: cutter torque, rock soil bearing capacity, total propelling force, left lower soil bin pressure, screw machine rotating speed and tunneling mileage; assuming that the future tunneling mileage is L meters, the characteristic Data values of cutterhead torque, rock soil bearing capacity, total propelling force, left lower soil bin pressure and screw machine rotating speed are the same as the characteristic Data values recorded in the last tool changing of the Data sample set Data1, and a Data sample set Data2 of the shield tunneling machine in the state of waiting to be tunneled is formed;
(6) calculating the accumulated equivalent wear W of a cutter head of a rear shield tunneling machine for a tunneling mileage of L metersL：
(6a) Carrying out logarithmic calculation on each kind of characteristic Data of the equivalent wear loss of the cutter head, which are influenced by the Data sample set Data2 in the state of the shield tunneling machine to be tunneled, to obtain a Data sample set Data2 ', and calculating the logarithmic value y of the accumulated equivalent wear loss of the cutter head of the shield tunneling machine after the tunneling mileage is L meters through the Data sample set Data 2':
y＝qL(Data2′)+ε
wherein ε represents the random error;
(6b) carrying out exponential calculation on a logarithmic value y of the accumulated equivalent wear loss of the cutter head of the rear shield machine with the tunneling mileage of L meters to obtain an accumulated equivalent wear loss W of the cutter head of the rear shield machine with the tunneling mileage of L metersL；
WL＝ey；
(7) Obtaining an evaluation prediction result of the wear of a cutter head of the shield tunneling machine:
according to the wear grade interval determined in the actual construction process, checking the accumulated equivalent wear W of a cutter head of the shield tunneling machine after the tunneling mileage is L metersLAnd in the abrasion grade interval, evaluating the abrasion degree of a cutter head of the shield machine after the shield machine tunnels for L meters.
The zone division of the shield tunneling machine cutterhead of the present invention is shown in fig. 4.
According to the method, based on the tool wear measurement record, the equivalent overall wear value of the cutter head is constructed by weighting and summing the wear amount of a single tool in different areas of the cutter head based on a data driving method, and compared with the traditional research taking the wear amount of a single tool as a prediction object, the method can more accurately establish the mapping relation between the observation data and the overall wear amount of the cutter head, and is convenient for evaluating and predicting the overall wear amount of the cutter head. According to the method, the Lasso regression is adopted to establish the prediction model, the regularized sparse solution screening function is achieved, the features which have weak contribution degree to the prediction result in the input process can be eliminated, the multiple collinearity problem which generally exists in a linear regression model is eliminated, the feature subset used by the final model is more accurate, the model prediction accuracy is higher, and the generalization capability is stronger.
The effects of the present invention will be further described below with reference to examples of the present invention.
The data set used in the example of the present invention is data of a left line shield interval from a station of liu five store of a building gate subway No. 3 to a station of east station, which is acquired by the group limited of the medium iron country from 7 months and 3 days in 2017 to 4 months and 10 days in 2018.
The method for evaluating and predicting the cutter head abrasion of the shield tunneling machine comprises the following steps:
(1) acquiring a Data sample set Data in a shield tunneling machine tunneling state:
(1a) two tool changing time points, the tool changing number of which is more than 30 and the tool changing number of which is less than 4, are respectively a 230 th ring and a 130 th ring from the construction record of the shield interval from the Liu five store station to the east boundary station, the 130 th ring to the 230 th ring are complete degradation intervals of the tool, and the tool changing data is changed for 38 times in total, wherein the tool changing data comprises 16 kinds of feature data of rock-soil bearing capacity feature data of a region to be constructed of the shield machine, shield machine tunneling control feature data acquired by a sensor in the shield machine construction process, shield machine state feature data and shield machine tunneling mileage data;
(1b) extracting Data in the Data set in the tunneling state, and removing Data in the Data set, wherein the total thrust of the shield tunneling machine is less than or equal to 0, and the rotating speed of a cutter head is less than or equal to 0, and the Data is used as a Data sample set Data of the shield tunneling machine in the tunneling state;
(2) preprocessing the Data sample set Data to obtain a Data sample set Data 1:
and carrying out abnormal value processing on each feature Data in the Data sample set Data, normalizing the abnormal value processing result, and then carrying out noise reduction processing on the normalized result to obtain the preprocessed Data sample set Data 1. The specific operation is as follows:
(2a) replacing the value of 0 in each kind of characteristic Data contained in the Data sample set Data with 0.00000001 to obtain a Data sample set Data' for processing the abnormal value of the Data sample set Data;
(2b) carrying out the most value normalization on each feature Data contained in the Data sample set Data 'by the following formula to obtain a Data sample set Data' after the most value normalization;
wherein z is*Represents the result of the most-valued normalization of each feature Data z in the Data sample set DatamaxAnd zminRespectively representing the maximum value and the minimum value of z;
(2c) and sampling each kind of characteristic Data contained in the Data sample set Data 'through a sliding window, calculating the root mean square value of the characteristic Data contained in the Data sample set Data' in each window, and using the calculation result as a substitute value of the characteristic Data contained in the Data sample set Data 'in the window to realize the noise reduction of each kind of characteristic Data of the Data'. The data denoising method comprises the following specific steps:
first, the length of the sliding window is set to m1Step length of window movement is s1Wherein m is1In [30,60 ]]Within the interval, take any positive integer, s1Value of (a) and m1Are equal.
Secondly, calculating the root mean square value of all data in the window after sliding once according to the following formula:
wherein d isiRepresents the RMS value, y, of all data within the ith sliding windowaAnd a represents the a data of the data in the window after the i sliding, and sigma represents the summation operation.
The Data sample set Data is preprocessed to obtain a Data sample set Data 1.
(3) Calculating equivalent wear W of cutter head of shield machine during cutter changing each timem：
(3a) Acquiring the abrasion loss of each cutter when each cutter is changed:
directly using the measured value of the normal wear cutter with the measured value;
secondly, for the normally worn cutter without the measured value, interpolating two adjacent measurement records, and approximately calculating the wear value;
for abnormal wear of the tool, such as eccentric wear and edge curl, the wear value will be determined according to the wear value
The position on the cutter head is approximately changed, the cutter in the outer ring area is 5mm, and the cutter in the front and central areas is 15 mm.
And fourthly, all the replacement records in the cutter head maintenance log are regarded as brand new cutters, and no abrasion is caused.
(3b) For different areas of a shield machine cutter head, the abrasion loss of a central hob, a front hob and an edge hob adopts coefficients alpha with different sizes, the abrasion coefficient of a cutter in an outer ring area is 3, and the abrasion coefficient of the cutter in the central area and the front area is 1.
And weighting and summing the wear quantities of all the cutters to obtain the equivalent overall wear quantity of the cutter head, and taking the equivalent overall wear quantity as a label of a Data sample set Data 1:
(4) computing coefficient vector q based on Lasso regressionL：
Calculating the equivalent wear W of the cutter headmLogarithmic value y ofmEstablishing a Lasso regression model by using the data sample set, and estimating a coefficient qLThe implementation steps are as follows:
(4a) for a given shield machine, the total wear of the cutterhead is affected by the original total wear value of the cutterhead, the tunneling length, geological characteristics and operating parameters. Therefore, the cumulative wear value of the cutter head can be represented by equation (1).
ΔW＝Wt-W0＝f(L,g1,…,gi,s1,…,sj,e1,…,ek) (1)
Wherein WtIs the total wear value of the cutter head at the time t, W0Is the original total abrasion value of the cutter head, L is the increment of the tunneling length, giFor the ith geological feature, sjIs the jth state characteristic of the shield machine, ekFor the kth tunneling operation parameter, f is a nonlinear function.
(4b) The relationship between the cumulative wear value of the cutter head and the influencing factors can be approximated as an exponential function, namely
Wherein, α, βi，γj，pkRespectively, are exponential powers, and epsilon is a random error.
(4c) Performing logarithm operation on two sides of the formula (2) by using a linear regression model, and then
lnΔW＝αlnL+β1lng1+…+βi lngi+γ1lns1+…+γjlnsj+p1 lne1+…+pk lnek+ε
(4d) By variable transformation, y ═ ln Δ W, x ═ x (lnL, ng) are defined1,...,lngi,lns1,...,lnsj,lne1,...,lnek)T，q＝(α,β1,...,βi,γ1,...,γj,p1,...,pk) Equation (3) can be converted to equation (4):
yi＝qxi+ε (4)
(4e) in formula (4), L is increased1Penalty term, estimated for equation (4) Lasso as:
wherein q represents a regression coefficient vector, R16The expression regression coefficient vector q is a column vector containing 16 elements, 16 expression Data is 16 kinds of characteristic Data which influence the equivalent abrasion loss of a cutterhead and are contained in the Data sample set Data, sigma represents a summation operation, lambda represents an adjusting coefficient, and x representsmAnd the influence factor pair value vector represents the accumulated equivalent wear quantity of the cutter head during the m-th cutter changing.
After the coefficient vector is calculated, assuming that other tunneling parameter characteristics are unchanged for a future tunneling distance, the tunneling mileage of each ring is set to be 1.2 meters, and a characteristic data value of 5 rings in the future is obtained. Such as the polyline shown in fig. 3. The abscissa in fig. 3 represents the number of rings, and the ordinate represents the wear amount of the cutter head.
TABLE 1 future 5-Loop assumptions data
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. A method for evaluating and predicting the abrasion of a cutter head of a shield machine is characterized in that the method for evaluating and predicting the abrasion of the cutter head of the shield machine selects a time point t when the last time of cutter changing is less than P from the recorded data of the replacement of a shield construction cutter0And the time point t when the number of tool changing is more than Q1The formed tool degradation interval [ t ]0,t1]Data of a Data sample set in a tunneling state of the inner shield tunneling machine; comprehensively preprocessing the Data sample set Data to obtain a Data sample set Data 1; calculating the equivalent abrasion loss of the cutter head when the shield machine changes the cutter every time, and taking the equivalent abrasion loss as a label; performing parameter estimation by using a multivariate linear regression model-Lasso regression model, removing insignificant influence factors according to parameter values, and finally establishing a calculation formula of the equivalent wear of the cutter head; and (3) evaluating and predicting the wear degree of the cutter head by using a formula after calculating the equivalent wear of the cutter head at a certain distance.
2. The method for evaluating and predicting shield machine cutterhead wear according to claim 1, wherein said method for evaluating and predicting shield machine cutterhead wear comprises the steps of:
acquiring a Data sample set Data in a shield tunneling machine tunneling state;
preprocessing the Data sample set Data to obtain a Data sample set Data 1;
step three, calculating the equivalent wear W of the cutter head of the shield tunneling machine when the cutter head is changed each timem；
Step four, calculating a coefficient vector q based on Lasso regressionL；
Step five, acquiring a Data sample set Data2 of the shield tunneling machine in a state of waiting tunneling;
sixthly, calculating the accumulated equivalent wear W of a cutter head of the shield tunneling machine after the tunneling mileage is L metersL；
And seventhly, obtaining an evaluation prediction result of the cutter head abrasion of the shield tunneling machine.
3. The method for evaluating and predicting the wear of the cutter head of the shield tunneling machine according to claim 2, wherein the step of obtaining the Data sample set Data in the tunneling state of the shield tunneling machine in the step one comprises:
(1) selecting a time point t with the last tool change number less than P from shield construction tool change recorded data0And the time point t when the number of tool changing is more than Q1The formed tool degradation interval [ t ]0,t1]H times of tool changing recording data in the system are carried out, wherein each time of tool changing recording data comprises 16 kinds of characteristic data of rock-soil bearing capacity characteristic data of a region to be constructed of the shield machine, shield machine tunneling control characteristic data acquired by a sensor in the shield machine construction process, shield machine PLC state characteristic data and shield machine tunneling mileage data; the shield tunneling machine tunneling control data comprises the total propelling force of the shield tunneling machine and the cutter head rotating speed; the shield tunneling machine PLC state characteristic data comprises a propelling speed, a cutter torque, a penetration degree, a screw machine rotating speed, a cutter rotating speed, a left lower soil bin pressure, a left middle soil bin pressure, a left upper soil bin pressure, an A group propelling pressure, a B group propelling pressure, a C group propelling pressure and a D group propelling pressure, P is less than or equal to 4, Q is more than or equal to 30, and H is more than or equal to 20;
(2) removing tool changing record Data which are less than or equal to 0 in total propelling force Data of shield tunneling machine tunneling control Data and less than or equal to 0 in cutter head rotating speed Data in H times of tool changing records, wherein the rest M tool changing record Data form Data sample set Data in a shield tunneling machine tunneling state;
the preprocessing of the Data sample set Data in the second step comprises:
abnormal value processing is carried out on each feature Data in the Data sample set Data, the abnormal value processing result is normalized, then noise reduction processing is carried out on the normalized result, and the preprocessed Data sample set Data1 is obtained;
the preprocessing of the Data sample set Data specifically comprises:
(1) replacing the value of 0 in each kind of characteristic Data contained in the Data sample set Data with 0.00000001 to obtain a Data sample set Data' for processing the abnormal value of the Data sample set Data;
(2) carrying out the most value normalization on each feature Data contained in the Data sample set Data 'by the following formula to obtain a Data sample set Data' after the most value normalization;
wherein z is*Represents the result of the most-valued normalization of each feature Data z in the Data sample set DatamaxAnd zminRespectively representing the maximum value and the minimum value of z;
(3) sampling each kind of characteristic Data contained in the Data sample set Data 'through a sliding window, calculating the root mean square value of the characteristic Data contained in the Data sample set Data' in each window, and using the calculation result as the substitute value of the characteristic Data contained in the Data sample set Data 'in the window to realize the noise reduction of each kind of characteristic Data of the Data'; wherein the data denoising comprises:
1) setting the length of the sliding window to m1Step length of window movement is s1(ii) a Wherein m is1In [30,60 ]]Taking any correction in intervalNumber, s1Value of (a) and m1Equal;
2) the rms value of all data in the window after each sliding is calculated as follows:
wherein d isiRepresents the RMS value, y, of all data within the ith sliding windowaRepresenting the a data in the window after the ith sliding, and sigma representing the summation operation;
the Data sample set Data is preprocessed to obtain a Data sample set Data 1.
4. The method for evaluating and predicting the wear of the cutter head of the shield tunneling machine according to claim 2, wherein the equivalent wear W of the cutter head of the shield tunneling machine during each cutter changing is calculated in the third stepmThe method comprises the following steps:
(1) acquiring the abrasion loss of each cutter when each cutter is changed:
1) setting a central area, a front area and an edge area of a cutter head of the shield tunneling machine to contain N cutters, wherein N is more than or equal to 46, judging whether each cutter is replaced during cutter changing each time according to the record of a cutter maintenance log, if so, the abrasion loss of the replaced cutter is 0, and if not, executing the step 2);
2) judging whether the abrasion loss of the tool which is not replaced is normal according to the abrasion record of the tool in the tool maintenance log, if so, executing the step 3); otherwise, taking the replacement threshold value of the tool which is not replaced and has abnormal wear loss as the wear loss of the tool when the tool is replaced each time; wherein, the replacement threshold value of the edge region cutter is 5mm, and the replacement threshold values of the front region cutter and the central region cutter are 15 mm;
3) judging whether the tool which is not replaced and has normal abrasion loss has an abrasion loss measured value, if so, taking the abrasion loss measured value as the abrasion loss of the tool during tool changing each time; otherwise, taking the interpolation result of 2 times of wear values of the cutter in the cutter maintenance log as the wear amount of the cutter during each cutter changing;
(2) for each timeThe cutter head N weights and sums the abrasion loss of the cutter during cutter changing to obtain the equivalent abrasion loss W of the cutter head during the m-th cutter changingm：
Wherein α represents the wear coefficient of the tool, the wear coefficient of the tool in the center region and the front region is 1, the wear coefficient of the tool in the edge region is 3, and wmnShows the wear amount of the nth tool when the mth tool is changed.
5. The method for evaluating and predicting shield tunneling machine cutterhead wear according to claim 2, wherein in step four, coefficient vector q is calculated based on Lasso regressionLThe method comprises the following steps:
calculating the equivalent wear W of the cutter head when the mth cutter changingmLogarithmic value y ofmAnd adopting a Lasso regression method to pass through the Data sample sets Data1 and WmLogarithmic value y ofmCalculating the coefficient vector q of the shield tunneling machine cutterhead accumulated equivalent wear loss logarithm value calculation formulaL：
ym＝lnWm；
Wherein q represents a regression coefficient vector, R16The expression regression coefficient vector q is a column vector containing 16 elements, 16 expression Data is 16 kinds of characteristic Data which influence the equivalent abrasion loss of a cutterhead and are contained in the Data sample set Data, sigma represents a summation operation, lambda represents an adjusting coefficient, and x representsmRepresenting the influence factor pair value vector of the accumulated equivalent wear quantity of the cutter head when the cutter is changed for the m time;
the step five of acquiring the Data sample set Data2 of the shield tunneling machine in the state of waiting tunneling comprises the following steps: screening out the characteristic Data of the equivalent wear extent of the cutter head which is finally influenced from the 16 characteristic Data of the equivalent wear extent of the cutter head which is contained in the Data sample set Data1 by adopting a Lasso regression regularization sparse screening method: cutter torque, rock soil bearing capacity, total propelling force, left lower soil bin pressure, screw machine rotating speed and tunneling mileage; assuming that the future tunneling mileage is L meters, the characteristic Data values of the cutterhead torque, the rock-soil bearing capacity, the total propelling force, the left lower soil bin pressure and the screw machine rotating speed are the same as the characteristic Data values recorded in the last tool changing of the Data sample set Data1, and a Data sample set Data2 of the shield tunneling machine in the state to be tunneled is formed.
6. The method for evaluating and predicting the wear of the cutter head of the shield tunneling machine according to claim 2, wherein the cumulative equivalent wear W of the cutter head of the shield tunneling machine after the tunneling mileage is calculated to be L meters in the sixth stepLThe method comprises the following steps:
(1) carrying out logarithmic calculation on each kind of characteristic Data of the equivalent wear loss of the cutter head, which are influenced by the Data sample set Data2 in the state of the shield tunneling machine to be tunneled, to obtain a Data sample set Data2 ', and calculating the logarithmic value y of the accumulated equivalent wear loss of the cutter head of the shield tunneling machine after the tunneling mileage is L meters through the Data sample set Data 2':
y＝qL(Data2′)+ε；
wherein ε represents the random error;
(2) carrying out exponential calculation on a logarithmic value y of the accumulated equivalent wear loss of the cutter head of the rear shield machine with the tunneling mileage of L meters to obtain an accumulated equivalent wear loss W of the cutter head of the rear shield machine with the tunneling mileage of L metersL；
WL＝ey；
The seventh step of obtaining the evaluation prediction result of the wear of the cutter head of the shield tunneling machine comprises the following steps:
according to the wear grade interval determined in the actual construction process, checking the accumulated equivalent wear W of a cutter head of the shield tunneling machine after the tunneling mileage is L metersLAnd in the abrasion grade interval, evaluating the abrasion degree of a cutter head of the shield machine after the shield machine tunnels for L meters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111670981.7A CN114382490A (en) | 2021-12-31 | 2021-12-31 | Shield tunneling machine cutter head wear assessment and prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111670981.7A CN114382490A (en) | 2021-12-31 | 2021-12-31 | Shield tunneling machine cutter head wear assessment and prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114382490A true CN114382490A (en) | 2022-04-22 |
Family
ID=81200363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111670981.7A Pending CN114382490A (en) | 2021-12-31 | 2021-12-31 | Shield tunneling machine cutter head wear assessment and prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114382490A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117851761A (en) * | 2024-03-08 | 2024-04-09 | 山东天工岩土工程设备有限公司 | Method and system for evaluating states of cutterheads of shield machine |
| CN117851761B (en) * | 2024-03-08 | 2024-05-14 | 山东天工岩土工程设备有限公司 | Method and system for evaluating states of cutterheads of shield machine |
-
2021
- 2021-12-31 CN CN202111670981.7A patent/CN114382490A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117851761A (en) * | 2024-03-08 | 2024-04-09 | 山东天工岩土工程设备有限公司 | Method and system for evaluating states of cutterheads of shield machine |
| CN117851761B (en) * | 2024-03-08 | 2024-05-14 | 山东天工岩土工程设备有限公司 | Method and system for evaluating states of cutterheads of shield machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Feng et al. | Tunnel boring machines (TBM) performance prediction: A case study using big data and deep learning | |
| Adoko et al. | Bayesian prediction of TBM penetration rate in rock mass | |
| CN108470095B (en) | TBM (tunnel boring machine) propulsion prediction method based on data-driven radial basis function model | |
| CN109815565A (en) | A kind of piecewise prediction method of comprehensive mining hydraulic bracket load | |
| Mondoro et al. | Prediction of structural response of naval vessels based on available structural health monitoring data | |
| Macias et al. | Influence of rock mass fracturing on the net penetration rates of hard rock TBMs | |
| CN114417697A (en) | Neural network-based TBM hob abrasion real-time prediction method and system | |
| CN107368463B (en) | Roadway nonlinear deformation prediction method based on fiber bragg grating sensor network data | |
| Garcia et al. | Decision support system for an intelligent operator of utility tunnel boring machines | |
| Wang et al. | Determination of the minimum sample size for the transmission load of a wheel loader based on multi-criteria decision-making technology | |
| Kazemi et al. | Application of dimensional analysis and multi-gene genetic programming to predict the performance of tunnel boring machines | |
| CN115358494B (en) | Danger early warning method for subway shield underpass construction | |
| CN112160761A (en) | Hard rock TBM cutter disc hob abrasion real-time evaluation method based on field parameters | |
| Yu et al. | Enhancing earth pressure balance tunnel boring machine performance with support vector regression and particle swarm optimization | |
| CN109101776B (en) | Foundation pit inverse analysis method based on lateral movement monitoring data of retaining wall | |
| Yong et al. | A dice similarity measure for TBM penetrability classification in hard rock condition with the intuitionistic fuzzy information of rock mass properties | |
| CN107153881B (en) | Drilling risk prediction method | |
| Li et al. | Cross-project utilisation of tunnel boring machine (TBM) construction data: A case study using big data from Yin-Song diversion project in China | |
| Li et al. | A LightGBM-based strategy to predict tunnel rockmass class from TBM construction data for building control | |
| CN111783308A (en) | Method for accurately predicting tunnel surrounding rock displacement | |
| CN114382490A (en) | Shield tunneling machine cutter head wear assessment and prediction method | |
| CN111476406B (en) | Oil-water well casing damage early warning method and device and storage medium | |
| CN117252086A (en) | Method, system and equipment for health evaluation and degradation prediction of shield tunneling machine cutterhead | |
| Vališ et al. | Drilling head knives degradation modelling based on stochastic diffusion processes backed up by state space models | |
| Kracík et al. | A statistical model for lifespan prediction of large steel structures |
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 |