Construction data processing method and system based on big data

Abstract

The invention relates to the technical field of data processing, in particular to a construction data processing method and system based on big data, and the method comprises the steps: synchronously collecting the load data of a drilling machine and the current data of a motor, setting historical load data for each piece of to-be-predicted load data, and calculating the prominence degree of the historical load data, the method comprises the following steps: acquiring current data, optimizing the prominence degree of historical load data by combining the change trend of the current data to obtain the credibility of the historical load data, accurately determining a reference value of to-be-predicted load data according to the credibility of all the historical load data, and reasonably adjusting the prediction range of the to-be-predicted load data by using the reference value to obtain the prediction range of the to-be-predicted load data. The prediction value of the to-be-predicted load data is accurately calculated, and the abnormal load data is judged according to the difference between the prediction value and the actual value, so that the accuracy of the operation state monitoring and fault prediction of the drilling machine is improved, and the more accurate and reliable processing of the data in the construction process is realized.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more particularly to a construction data processing method and system based on big data. Background Art

[0002] In the process of construction, covering various stages such as project initiation, design, procurement, construction and acceptance, a huge amount of data will be generated. The sources of these data include information collected by sensors, records of construction logs, details of material procurement and labor allocation. Drilling is a basic and critical link in the construction process. The drilling machine is the core heavy equipment. Its stable operation is closely related to the progress, cost control and safety of the entire construction project. Therefore, it is of great significance to accurately analyze and process the relevant data of the drilling machine during the construction process, analyze its operating status in detail, predict potential safety hazards in advance, and implement maintenance measures in time to ensure the normal and orderly development of construction.

[0003] In the existing technology of equipment fault prediction, the operation data of the equipment is usually collected first, and then the HTFE prediction algorithm is used. The prediction algorithm predicts the future operation data of the equipment based on the past historical data of the equipment operation, so as to determine whether the equipment has potential faults. For example, the existing Chinese patent application document with the publication number CN119146267A discloses a water supply valve control method and system based on fault monitoring, which collects the pressure and valve diameter data of the valve to obtain the pressure sequence and valve diameter sequence respectively, and then predicts these sequences at the historical moment based on the HTFE algorithm to obtain the predicted values ​​of the pressure and valve diameter at the current moment, and uses the reliability of the predicted value at the current moment to correct the sum of the difference between the predicted value and the actual value, so as to obtain the degree of fault at the current moment.

[0004] However, the HTFE prediction algorithm used in the above technical solution has a defect. Specifically, the prediction algorithm calculates the prediction range of the current data based on the prediction range of the previous data and the actual value of the previous data, and then determines the prediction value of the current data. In the actual construction data environment, especially for the collection of drilling machine load data, since the drilling operation will inevitably produce relatively strong mechanical vibrations, this vibration is very likely to interfere with the signal collection of the load sensor, thereby causing the generation of load noise data. Once the noise data is mixed in, the actual value of the previous load data is very likely to be contaminated and converted into noise data. In this case, the predicted value of the current load data calculated by the HTFE algorithm will deviate from the actual situation, and further cause deviations in the prediction of the overload failure of the drilling machine, thereby affecting the subsequent load data abnormality judgment and the prediction of the overload failure of the drilling machine, and cannot meet the requirements for data accuracy and reliability during the construction process. Summary of the invention

[0005] In order to solve the problem that the strong mechanical vibration generated by drilling operations in the current construction environment often interferes with the signal collection of load sensors, causing the collected drilling machine load data to be mixed with noise, affecting the prediction accuracy of the traditional HTFE algorithm for the drilling machine operation data, and thus leading to the inability to accurately predict the potential failures of the drilling machine, affecting the construction progress and safety, the present invention proposes a construction data processing method based on big data, including: Collect the load data of the drilling machine during the construction process and the current data of the motor at the same time, take each load data as the load data to be predicted, and use the HTFE prediction algorithm to obtain the prediction range of each load data to be predicted; Setting multiple historical load data for each load data to be predicted, calculating the prominence of each historical load data, and evaluating the credibility of each historical load data according to the prominence of each historical load data and the load data in the adjacent data segment of the historical load data, as well as the change trend of the corresponding current data in the adjacent data segment; Based on the credibility of all historical load data of the load data to be predicted, a reference value for adjusting the prediction range of the load data to be predicted is determined, the prediction range of the load data to be predicted is adjusted using the reference value, the prediction value of the load data to be predicted is calculated according to the adjusted prediction range of the load data to be predicted, and the abnormal load data is determined according to the difference between the predicted value and the actual value of each load data, so as to realize the processing of the data of the drilling machine in the construction process.

[0006] The above technical solution collects the load data of the drilling machine during the construction process, which is the key information reflecting its working state, and the motor current data is closely related to it, which can reflect the operating condition of the drilling machine from the side. The load data is taken as the object to be predicted, and the HTFE algorithm is used to preliminarily determine its prediction range, which is the basis for subsequent more accurate prediction and analysis. And further, considering the importance of historical data to the current prediction, not all historical data have the same reliability. By calculating the prominence and combining the change trend of the load and current data of the adjacent data segment to evaluate the credibility, the quality of different historical data can be distinguished. The prominence can reflect the abnormality of a certain historical data relative to other data, while the change trend reflects the rationality and stability of the data in the time series. The combination of the two can screen out those more reliable historical data and exclude the interference of unreliable historical data on the prediction due to factors such as noise and abnormal working conditions. And further, after determining the credibility of the historical data, a reference value for adjusting the prediction range is generated based on this, and the prediction range originally obtained by the HTFE algorithm is corrected to make the prediction range more in line with the actual situation. Then, a more accurate prediction value is calculated based on the adjusted prediction range. Finally, abnormal load data is identified by comparing the difference between the predicted value and the actual value, thereby realizing effective processing of construction data and achieving the purpose of accurately monitoring the operating status of the drilling machine and discovering potential problems.

[0007] Preferably, the credibility of each historical load data satisfies the following relationship: ; In the formula, For the The load data to be predicted The credibility of historical load data, For the The load data to be predicted The prominence of historical load data, For the The load data to be predicted The value of the current data corresponding to the collection time of the historical load data, For the The load data to be predicted The mean of the adjacent data segments of the historical load data, For the The load data to be predicted The value of historical load data, For the The load data to be predicted The average value of the current data in the adjacent data segment of the historical load data, is the absolute value symbol, is a natural exponential function.

[0008] The various parameters in the above technical solutions reflect the inherent relationship between different data. The mean values ​​of current data and load data in adjacent data segments and their relative relationship are used to measure the credibility of historical load data, which reflects the physical relationship between load and current during the operation of the drilling machine, that is, the current change of the motor is often related to the load change of the drilling machine. Therefore, this data association logic in actual operation is introduced into the credibility assessment, making the credibility calculation more in line with the actual working conditions.

[0009] Preferably, the calculation formula for the prominence degree of each historical load data is: ; In the formula, For the The load data to be predicted The prominence of historical load data, For the The load data to be predicted The prediction error of historical load data is For the The load data to be predicted The value of historical load data, For the The load data to be predicted The mean of the adjacent data segments of the historical load data, is a hyperparameter, For the The load data to be predicted The change of historical load data, The change in the historical load data is equal to The historical load data and The absolute value of the difference between the historical load data.

[0010] The above technical solution not only focuses on the static value of historical load data, but also considers its dynamic change characteristics. In actual construction, the load of the drilling machine will change with the change of working conditions. Capturing this dynamic characteristic helps to more accurately identify those data that show abnormalities during the change process, so as to better adapt to the complex working conditions and data fluctuations in the construction process, and make the evaluation of historical load data more in line with the actual operation.

[0011] Preferably, the reference value of the prediction range of the load data to be predicted is adjusted to satisfy the following relationship: ； In the formula, To adjust the The reference value of the prediction range of the load data to be predicted, For the The total number of historical load data to be predicted, For the The load data to be predicted The credibility of historical load data, For the The sum of the credibility of all historical load data of the load data to be predicted, For the The load data to be predicted The actual value of historical load data.

[0012] The above technical solution makes the historical load data with high credibility have a greater influence in determining the reference value, while the historical load data with low credibility has relatively less influence. This credibility-based weight distribution mechanism can effectively utilize reliable historical data, reduce the interference of unreliable data on the adjustment of the forecast range, and make the reference value better reflect the actual situation.

[0013] Preferably, the adjacent data segment of the historical load data is acquired in the following manner: each historical load data and a plurality of load data immediately before the acquisition time are combined to form the adjacent data segment of the historical load data.

[0014] Preferably, the method for adjusting the prediction range of the load data to be predicted by using the reference value is: Jordi The upper limit of the prediction range of the load data to be predicted is less than , The upper limit of the prediction range of the load data to be predicted is equal to ; If The lower limit of the forecast range of the load data to be forecasted is greater than , The lower limit of the forecast range of the load data to be forecasted is equal to .

[0015] The adjustment method of the above technical solution constrains the upper and lower limits of the prediction range according to the reference value to ensure that the prediction range does not deviate from the reasonable range determined based on the characteristics of historical data. If the upper limit of the prediction range is too small or the lower limit is too large, it does not conform to the actual situation reflected by the historical data compared with the reference value. By adjusting it to the reference value, the prediction range can be more consistent with the inherent laws and trends of the data, avoiding unreasonable prediction ranges caused by factors such as the limitations of the prediction algorithm itself or data noise.

[0016] Preferably, the method for calculating the predicted value of the load data to be predicted according to the adjusted prediction range of the load data to be predicted is:

[0017] In the formula, For the The predicted value of the load data to be predicted, For the The upper limit of the forecast range after the load data to be forecasted is adjusted. For the The lower limit of the forecast range after the load data to be forecasted is adjusted. , , These are the parameters of the HTFE prediction algorithm.

[0018] Preferably, the method for determining abnormal load data according to the difference between the predicted value and the actual value of each load data is: The normalized value of the difference between the predicted value and the actual value of each load data is obtained. If the normalized value is greater than a preset difference threshold, the load data is abnormal load data.

[0019] Preferably, after determining the abnormal load data according to the difference between the predicted value and the actual value of each load data, the following operations are further performed: Continuous monitoring: if N abnormal load data appear within a certain minute, an early warning will be issued to notify relevant personnel to perform maintenance on the drilling machine. N is the preset value.

[0020] The present invention also provides a construction data processing system based on big data, the construction data processing system includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of any one of the construction data processing methods.

[0021] The present invention has the following effects: When determining the prediction range of each load data to be predicted, the present invention introduces multiple historical load data of the load data to be predicted, takes into account the characteristics and change trends of the historical load data, and combines the change trends of the corresponding current data to accurately evaluate the credibility of the historical load data, and calculates the prediction range by weighted average of multiple historical load data. It can effectively identify and eliminate the interference of noise data, thereby ensuring that the prediction range calculated by the HTFE algorithm more accurately reflects the actual load change trend of the drilling machine, thereby improving the accuracy of the prediction of the drilling machine's operating data, making the prediction results of the drilling machine's potential faults more reliable, and to a certain extent ensuring the normal progress and safety of construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a schematic flow chart of the method of the present invention; Figure 2 It is a schematic diagram of the method flow of step S2 of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] Reference Figure 1 The present invention provides a construction data processing method based on big data, comprising the steps of: -step : S1: Collect the load data of the drilling machine and the current data of the motor during the construction process.

[0026] In one embodiment, a high-precision force sensor is installed on the drill bit of the drilling machine to accurately collect the load data of the drilling machine in real time. At the same time, a current sensor is used to synchronously monitor the current data of the motor in real time. To ensure the validity and relevance of the data, the two types of data are collected in the same time period and accurately correspond to each other on the time axis. The collection time is set to one hour, and the collection frequency is fixed to once per second, so as to obtain high-resolution and time-series matching drilling machine load and motor current data, providing a solid data foundation for subsequent analysis and processing.

[0027] S2: Analyze the numerical variation characteristics of the load data of the drilling machine and the current data of the motor, optimize the method of adjusting the prediction range of the load data to be predicted by the HTFE model, and obtain the prediction range after the adjustment of the load data to be predicted; In one embodiment, the method for optimizing the manner in which the HTFE model adjusts the prediction range of the load data to be predicted is as follows: Figure 2 As shown: S21: Analyze the numerical characteristics of each historical load data of the load data to be predicted, and obtain the prominence degree of each historical load data of the load data to be predicted.

[0028] Specifically, take any load data as the load data to be predicted, and replace the load data before the load data to be predicted with load data, as all the historical load data of the load data to be predicted, (Empirical value). When collecting drilling machine load data, noise data often presents obvious characteristics, that is, its value will fluctuate rapidly in a short period of time, and extremely high or extremely low values ​​will appear that are significantly different from normal operating data. Therefore, when analyzing the prominence of each historical load data, the following key factors are comprehensively considered: First, the error size generated when each historical load data is predicted using the HTFE prediction algorithm. A larger prediction error indicates that the historical load data deviates from the expected value based on the historical trend to a high degree; second, the value of the historical load data is compared with the mean of its adjacent data segments. The greater the degree of deviation of the historical load data from the mean, the more obvious the particularity of the historical load data; finally, the numerical change between the historical load data and the historical load data at the previous moment is examined. If the change is large, this may also imply that the historical load data is interfered by abnormal factors such as noise, resulting in a sudden change in the value. Combining these three factors, the prominence of each historical load data is determined.

[0029] In one embodiment, for each historical load data, the adjacent data segment is obtained as follows: the historical load data and the 50 (empirical value) load data immediately before the collection time are combined to form its adjacent data segment. However, if the number of load data before the collection time of a certain historical load data is less than 50, then the load data within two minutes in advance is selected to supplement it, so as to ensure that the adjacent data segment of each historical load data can be fully constructed, thereby providing a stable and reliable data foundation for subsequent data analysis based on the adjacent data segment, and ensuring the consistency and accuracy of the entire construction data processing process.

[0030] In one embodiment, the prominence of each historical load data is calculated according to the following formula:

[0031] In this formula, For the The load data to be predicted The prominence of historical load data, For the The load data to be predicted The prediction error of historical load data is For the The load data to be predicted The value of historical load data, For the The load data to be predicted The mean of the adjacent data segments of the historical load data, is a hyperparameter, (Experience points), exists to prevent A situation of 0 occurs. For the The load data to be predicted The change of historical load data, The change in the historical load data is equal to The historical load data and The absolute value of the difference between the historical load data.

[0032] In this formula, Intuitive reflection The load data to be predicted The values ​​of historical load data fluctuate abnormally. The larger the The greater the possibility that the historical load data has abnormal fluctuations, the greater the probability that the The more likely a historical load data is to be potential noise data, the greater its prominence. It measures the deviation of historical load data from the mean of adjacent data segments. A larger deviation indicates that the historical load data is abnormal in a local range. The greater the deviation from the mean, the higher the possibility of becoming noise data and the greater the degree of prominence. This consideration based on data distribution characteristics makes abnormal judgment more scientific. Specifically, The larger the The more the value of the historical load data deviates from the The average of the adjacent data segments of the historical load data indicates that The more likely a historical load data is to be potential noise data, the greater its prominence. The focus is on the change between each historical load data and the load data at the previous moment. During the construction process, under normal working conditions, the change of load data is relatively stable, while noise interference will cause the load data to mutate. It can effectively capture this dynamic change, timely discover abnormal data points caused by sudden noise, further strengthen the ability to identify potential noise data, and enhance the judgment of data stability and reliability. The larger the The greater the value change between the historical load data and the load data collected at the last moment, the greater the value change. The more the historical load data deviates from the The greater the credibility of the mean of the adjacent data segments of the historical load data, the The more likely a historical load data is potential noise data, the greater its prominence will be.

[0033] The prominence of each historical load data determined by the above content can effectively screen and grade the historical load data. The historical load data with a high degree of prominence is marked as high-risk noise data, which can be treated with caution or corrected in subsequent data processing, thereby reducing the adverse effects of noise data on the prediction range and prediction value calculation, improving the accuracy of load data prediction, and making the drilling machine operation status analysis, abnormality judgment and fault prediction based on these data more accurate and reliable.

[0034] S22: According to the prominence of each historical load data, the load data in the adjacent data segment of the historical load data, and the change trend of the current data corresponding to the adjacent data segment, the prominence of each historical load data is optimized to obtain the credibility of each historical load data.

[0035] After a series of analysis steps, although the prominence of each historical load data for each load data to be predicted is obtained, this prominence is only determined based on the numerical performance of each historical load data itself. It is impossible to distinguish whether it is caused by noise data interference or large fluctuations in load data.

[0036] This step takes into account that drilling machines are usually driven by electric motors, and there is a positive proportional relationship between the load of the motor and its current or power consumption. Specifically, during drilling operations, when the formation resistance increases and the load of the drilling machine increases, the motor has to output more power to cope with it, and the current will increase accordingly, which reflects the close and actual logical connection between the two. Therefore, on this basis, we further analyze the numerical performance of each historical load data and its corresponding current data, and observe the correlation between the two. If the positive correlation between a certain historical load data and its corresponding current data is worse, it means that this historical load data is more likely to be an anomaly caused by noise interference, rather than a real load change under normal construction conditions, then the credibility assigned to this historical load data should be lower.

[0037] In this way, the prominence degree previously derived solely based on the historical load data itself is optimized to obtain a credibility that better reflects the true reliability of the historical load data, so that these historical data can be more accurately used in subsequent operations such as predicting load data and judging anomalies, reducing problems such as inaccurate predictions caused by misjudgment of data properties (taking noise data as real abnormal data or vice versa).

[0038] In general, based on the prominence of each historical load data, further analysis and optimization is performed in combination with the motor current data, so as to more accurately judge the reliability of each historical load data.

[0039] In one embodiment, the credibility of each historical load data satisfies the following relationship:

[0040] In the formula, For the The load data to be predicted The credibility of historical load data, For the The load data to be predicted The prominence of historical load data, For the The load data to be predicted The value of the current data corresponding to the collection time of the historical load data, For the The load data to be predicted The mean of the adjacent data segments of the historical load data, For the The load data to be predicted The value of historical load data, For the The load data to be predicted The average value of the current data corresponding to the adjacent data segments (based on the acquisition time) of the historical load data, is the absolute value symbol, is a natural exponential function.

[0041] In this formula, The larger the The load data to be predicted The greater the possibility that historical load data is noise data rather than real data, the smaller its corresponding credibility. Quantified the The numerical ratio between the adjacent data segment of the historical load data and the current data segment corresponding to the adjacent data segment, Indicates The reference value of historical load data is The larger the absolute value of the difference, the The worse the positive correlation between the numerical performance of the historical load data and its corresponding current data, the The greater the possibility that the historical load data is noise data rather than real data, the The corresponding credibility of historical load data will be lower.

[0042] In summary, by introducing current data and the mean of historical load data and its adjacent data segments, a mechanism that reflects the internal connection between load data and current data is constructed. In actual construction, as mentioned above, when the motor drives the drilling machine, the load and current have a close positive correlation. This formula is based on this actual working condition and reflects this relationship in mathematical form, that is, by calculating the absolute value of the difference between the reference value and the historical load data itself to measure the correlation between the two, so that the calculation of credibility is more in line with the operating principle of the drilling machine and the change law of actual data, and possible noise data interference is screened out, thereby improving the accuracy of subsequent prediction of drilling machine load data and more accurately reflecting the actual load changes of the drilling machine.

[0043] S23: Determine a reference value for adjusting a prediction range of the load data to be predicted based on the credibility of all historical load data of the load data to be predicted.

[0044] After obtaining the credibility of each historical load data of each load data to be predicted. In this step, a weighted average calculation is performed based on the indicator and the actual value of each historical load data to obtain a reference value for adjusting the prediction range of the load data to be predicted, and in subsequent steps, the prediction range of the load data to be predicted is accurately adjusted based on this reference value. If the credibility of a historical load data is greater, it means that the possibility that this historical load data point belongs to noise data is smaller, then the actual value of this historical load data should have a greater weight when calculating the reference value.

[0045] In one embodiment, the reference value of the prediction range of the load data to be predicted is adjusted to satisfy the following relationship:

[0046] In the formula, To adjust the The reference value of the prediction range of the load data to be predicted, For the The total number of historical load data to be predicted, the empirical value , that is, 10 historical load data are selected for each load data to be predicted. For the The load data to be predicted The credibility of historical load data, For the The sum of the credibility of all historical load data of the load data to be predicted, For the The load data to be predicted The actual value of historical load data.

[0047] This formula calculates the reference value by combining the credibility of each historical load data with the actual value, reflecting a weighted average idea based on credibility. This means that instead of simply taking a conventional average of the actual values ​​of all historical load data, corresponding weights are assigned according to the reliability of each historical load data, so that more reliable data can play a greater role in determining the reference value, which is more in line with the logic of focusing on the use of reliable data in actual data processing, and scientifically integrates the information contained in the historical load data.

[0048] In summary, the significance of adjusting the reference value of the prediction range of the load data to be predicted is: Improve the rationality of forecast range adjustment: The reference value calculated by this credibility-weighted average method provides a scientific and reasonable basis for the subsequent forecast range adjustment of the forecast load data.

[0049] Enhanced resistance to noise data: When faced with possible mixed noise data, since low-credibility data has a smaller weight when calculating the reference value, its impact on the reference value is effectively suppressed, and the reference value will not deviate from the normal range due to interference from individual noise data. In this way, when using the reference value to adjust the prediction range, the adverse effects of noise data can be reduced.

[0050] S24: Adjust the prediction range of the load data to be predicted by using the above reference value.

[0051] In one embodiment, the prediction range of the load data to be predicted is obtained using the HTFE prediction algorithm: First, perform initialization: Get the first The prediction range of the load data to be predicted is taken as the initial condition. The specific method is as follows: The first The 20 load data before the first load data to be predicted constitute the load data sequence of the first load data to be predicted. The mean value of the load data sequence is taken as the first load data sequence. The maximum and minimum values ​​in the load data sequence are taken as the predicted values ​​of the load data to be predicted. The upper limit and lower limit of the maximum prediction range of the load data to be predicted are used to form the first The prediction range of the load data to be predicted.

[0052] Next, for the Load data to be predicted , the HTFE prediction algorithm is based on The actual value of the previous load data of the load data to be predicted , the prediction error of the previous load data The method to obtain the forecast range of the load data to be forecasted is as follows: Calculate the The initial forecast value of the load data to be forecasted : ; In this formula, is the error factor of the HTFE prediction algorithm, .

[0053] The first The prediction range of the load data to be predicted is: ; ; In the above formula, , Respectively The upper and lower limits of the prediction range of the load data to be predicted, , Respectively The upper and lower limits of the prediction range of the load data to be predicted, is the influencing factor of the prediction error range of the HTFE prediction algorithm, .

[0054] In one embodiment, the method for adjusting the prediction range of the load data to be predicted by the traditional HTFE algorithm is: when the upper limit value of the prediction range of the load data to be predicted is less than the initial prediction value of the load data to be predicted, the upper limit value of the prediction range of the load data to be predicted is set to be equal to the initial prediction value of the load data to be predicted; when the lower limit value of the prediction range of the load data to be predicted is greater than the actual value of the previous load data, the lower limit value of the prediction range of the load data to be predicted is set to be equal to the initial prediction value of the load data to be predicted.

[0055] Specifically, it is to ensure that the predicted value of the load data to be predicted can cover the actual value of the previous load data. ,when Less than ,make equal ,when Greater than ,make equal .

[0056] This method cannot guarantee the actual value of the previous load data. Whether it is a true value is easily affected by noise, which leads to the inability to accurately calculate the prediction range of the load data to be predicted, thereby affecting the accuracy of the subsequent calculation of the predicted value of the load data to be predicted.

[0057] In one embodiment, the method for adjusting the prediction range of the load data to be predicted in this step is: When the upper limit value of the prediction range of the load data to be predicted is less than the reference value for adjusting the prediction range of the load data to be predicted, the upper limit value of the prediction range of the load data to be predicted is set equal to the reference value, and when the lower limit value of the prediction range of the load data to be predicted is greater than the reference value for adjusting the prediction range of the load data to be predicted, the lower limit value of the prediction range of the load data to be predicted is set equal to the reference value. This adjustment is to ensure that the prediction range of each load data to be predicted can cover the reference value for adjusting the prediction range of the load data to be predicted.

[0058] For For each load data to be predicted, if The upper limit of the prediction range of the load data to be predicted , The upper limit of the prediction range of the load data to be predicted ; If The lower limit of the prediction range of the load data to be predicted , The lower limit of the prediction range of the load data to be predicted .

[0059] By adjusting the prediction range of the load data to be predicted through the above-mentioned reference values, compared with the traditional method of adjusting the prediction range of the load data to be predicted only according to the previous load data, it can better adapt to the complex situations such as noise and fluctuation in the actual construction data, and make the adjustment of the prediction range more in line with the real laws reflected by the historical data, so as to ensure that the prediction range can be within a relatively accurate and reasonable range, avoid deviations in the prediction range due to unreasonable reference values, and help to more accurately predict the load data of the drilling machine, timely discover potential abnormal situations, and ensure the smooth progress of construction.

[0060] S3: Use the prediction range adjusted by the load data to be predicted to predict the load data and warn of the fault status of the drilling machine according to the prediction result.

[0061] In one embodiment, the method for the HTFE algorithm to predict the load data to be predicted using the prediction range adjusted by the load data to be predicted is:

[0062] In the formula, For the The predicted value of the load data to be predicted, For the The upper limit of the forecast range after the load data to be forecasted is adjusted. For the The lower limit of the forecast range after the load data to be forecasted is adjusted. , , These are the parameters of the HTFE prediction algorithm. , , It is based on It is determined by the historical trend of the load data to be predicted.

[0063] In one embodiment, , , The method for determining is: Get the load data to be predicted Load data, , For setting The total number of historical load data to be predicted, (Experience points); Analyze the changing trend of these 100 load data: If it is monotonically increasing, it means that The historical trend of the load data to be predicted is growth type. At this time: , , ; If it is monotonically decreasing, The historical trend of the load data to be predicted is of decay type. At this time: , , ; If it is neither monotonically increasing nor monotonically decreasing, then: No. The historical trend of the load data to be predicted is irregular. , , .

[0064] In one embodiment, the method for early warning of the fault state of the drilling machine according to the prediction result is: Determine abnormal load data: obtain the normalized value of the difference between the predicted value and the actual value of each load data. If the normalized value is greater than the preset difference threshold of 0.96 (empirical value), the load data is abnormal load data. If the normalized value is not greater than the preset difference threshold of 0.96, the load data is normal load data.

[0065] Continuous monitoring: if N abnormal load data appear within a certain minute, an early warning will be issued to notify relevant personnel to perform maintenance on the drilling machine. N is 5 (empirical value).

[0066] The present invention also provides a construction data processing system based on big data, the construction data processing system includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement any step of the construction data processing method.

[0067] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0068] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A construction data processing method based on big data, characterized in that: include: Collect the load data of the drilling machine during the construction process and the current data of the motor at the same time, take each load data as the load data to be predicted, and use the HTFE prediction algorithm to obtain the prediction range of each load data to be predicted; Setting multiple historical load data for each load data to be predicted, calculating the prominence of each historical load data, and evaluating the credibility of each historical load data according to the prominence of each historical load data and the load data in the adjacent data segment of the historical load data, as well as the change trend of the corresponding current data in the adjacent data segment; Based on the credibility of all historical load data of the load data to be predicted, a reference value for adjusting the prediction range of the load data to be predicted is determined, the prediction range of the load data to be predicted is adjusted using the reference value, the prediction value of the load data to be predicted is calculated according to the adjusted prediction range of the load data to be predicted, and the abnormal load data is determined according to the difference between the predicted value and the actual value of each load data, so as to realize the processing of the data of the drilling machine in the construction process.

2. The construction data processing method based on big data according to claim 1 is characterized in that: The credibility of each historical load data satisfies the following relationship: ； In the formula, For the The load data to be predicted The credibility of historical load data, For the The load data to be predicted The prominence of historical load data, For the The load data to be predicted The value of the current data corresponding to the collection time of the historical load data, For the The load data to be predicted The mean of the adjacent data segments of historical load data, For the The load data to be predicted The value of historical load data, For the The load data to be predicted The average value of the current data in the adjacent data segment of the historical load data, is the absolute value symbol, is a natural exponential function.

3. The construction data processing method based on big data according to claim 2 is characterized in that: The calculation formula for the prominence of each historical load data is: ； In the formula, For the The load data to be predicted The prominence of historical load data, For the The load data to be predicted The prediction error of historical load data is For the The load data to be predicted The value of historical load data, For the The load data to be predicted The mean of the adjacent data segments of historical load data, is a hyperparameter, For the The load data to be predicted The change of historical load data, The change in the historical load data is equal to The historical load data and The absolute value of the difference between the historical load data.

4. The construction data processing method based on big data according to claim 2 is characterized in that: The reference value of the prediction range of the load data to be predicted is adjusted to satisfy the following relationship: ； In the formula, To adjust the The reference value of the prediction range of the load data to be predicted, For the The total number of historical load data to be predicted, For the The load data to be predicted The credibility of historical load data, For the The sum of the credibility of all historical load data of the load data to be predicted, For the The load data to be predicted The actual value of historical load data.

5. The construction data processing method based on big data according to claim 2 is characterized in that: The method for obtaining the adjacent data segment of historical load data is as follows: Each historical load data and a plurality of load data immediately before the collection time are combined to form a contiguous data segment of the historical load data.

6. The construction data processing method based on big data according to claim 4 is characterized in that: The method for adjusting the prediction range of the load data to be predicted using the reference value is: Jordi The upper limit of the prediction range of the load data to be predicted is less than , Order The upper limit of the prediction range of the load data to be predicted is equal to ; Jordi The lower limit of the forecast range of the load data to be forecasted is greater than , Order The lower limit of the forecast range of the load data to be forecasted is equal to .

7. The construction data processing method based on big data according to claim 6 is characterized in that: The method for calculating the predicted value of the load data to be predicted according to the predicted range after the load data to be predicted is: ； In the formula, For the The predicted value of the load data to be predicted, For the The upper limit value of the forecast range after the load data to be forecasted is adjusted. For the The lower limit of the forecast range after the load data to be forecasted is adjusted. , , These are the parameters of the HTFE prediction algorithm.

8. The construction data processing method based on big data according to claim 7 is characterized in that: The method for determining abnormal load data based on the difference between the predicted value and the actual value of each load data is: The normalized value of the difference between the predicted value and the actual value of each load data is obtained. If the normalized value is greater than a preset difference threshold, the load data is abnormal load data.

9. The construction data processing method based on big data according to claim 8 is characterized in that: After determining the abnormal load data based on the difference between the predicted value and the actual value of each load data, the following operations are performed: Continuous monitoring: if N abnormal load data appear within a minute, an early warning will be issued to notify relevant personnel to perform maintenance on the drilling machine. N is the preset value.

10. A construction data processing system based on big data, characterized in that: The construction data processing system includes a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the steps of the construction data processing method according to any one of claims 1 to 9.

Images