Slurry state monitoring method and equipment, computer equipment and medium

Abstract

The invention discloses a mud state monitoring method and equipment, computer equipment and a medium, which are used for solving the problems of incapability of real-time monitoring, relatively large error and difficulty in timely processing in manual inspection. The method comprises the following steps: acquiring state parameters of slurry through monitoring equipment; analyzing the state parameters based on a neural network model; and adjusting equipment is controlled to adjust the slurry state according to the analysis result. According to the method, the state of the mud can be monitored in real time, the state of the mud is predicted through the neural network, so that the state of the mud is intelligently regulated and controlled, the mud can be adjusted at the initial stage when the performance of the mud is abnormal, and compared with a traditional manual inspection mode, the method can be independent of manual experience, and the efficiency is improved. The mud state can be adjusted in advance, delay caused by manual intervention is avoided, the mud is always in the optimal state, the slag carrying capacity and the wall protection stability of the mud are guaranteed, and therefore the construction quality of a pile foundation is guaranteed, and the construction safety and efficiency are improved.

Description

Technical Field

[0001] This application relates to the field of building construction technology, and in particular to a method, device, computer equipment, and medium for monitoring the state of mud. Background Technology

[0002] In the construction of bridges and other buildings, pile foundations serve as the foundation of the load-bearing structure, bearing the weight of the entire building. The quality of pile foundation construction directly affects stability and safety. During the pile foundation drilling process, mud is an important wall-protecting medium. It not only supports the pile hole wall and prevents collapse, but also removes rock cuttings during drilling, keeping the hole wall clean and ensuring the smooth progress of pile foundation construction.

[0003] Currently, the performance status of drilling mud is typically monitored periodically by construction personnel. However, manual monitoring is not timely enough to achieve real-time monitoring, and there may be long gaps in monitoring. When the mud condition changes, it is difficult to effectively predict and prevent risks, making it difficult to take effective measures in a timely manner, missing the optimal treatment window, leading to a decline in the quality of pile foundation construction, and even construction accidents such as borehole collapse. Furthermore, manual monitoring and adjustment are easily affected by the external environment and the experience of the operators, resulting in large errors and low efficiency. Summary of the Invention

[0004] This application provides a method, device, computer equipment, and medium for monitoring the state of mud, in order to solve the technical problems of existing technologies where manual inspection cannot monitor in real time, has large errors, and is difficult to handle in a timely manner.

[0005] On the one hand, embodiments of this application provide a method for monitoring the state of mud, including: The state parameters of the mud are obtained through monitoring equipment; The state parameters are analyzed based on a neural network model; Based on the analysis results, the control and adjustment equipment is used to adjust the state of the mud.

[0006] This application embodiment can monitor the state of the mud in real time and predict the state of the mud through a neural network, thereby realizing intelligent control of the mud state. It can adjust the mud at the initial stage when abnormal mud performance occurs. Compared with the traditional manual inspection method, it does not rely on human experience and can adjust the mud state in advance, avoiding the delay caused by human intervention. It keeps the mud in the optimal state at all times, ensuring the mud's slag carrying capacity and wall stability, thereby ensuring the construction quality of the pile foundation and improving the safety and efficiency of construction.

[0007] In one implementation of this application, the analysis of the state parameters based on a neural network model includes: The state parameters are input into the neural network model; The output data of the neural network model is used to predict the state of mud in a future preset time period.

[0008] In this embodiment, a neural network prediction model is used to predict the changes in mud over a preset period of time through real-time data analysis. This allows for the detection of potential risks in the mud and the issuance of early warning signals to notify personnel or activate an automatic adjustment mechanism for timely handling. Compared with traditional manual judgment, this reduces response time and improves construction safety.

[0009] In one implementation of this application, before the step of inputting the state parameters into the neural network model, the method further includes: Obtain historical state data of the mud, and normalize the historical state data; Based on the processed historical state data, key feature vectors of mud state changes over time are extracted. The key feature vectors are used as input data, and the predicted mud state for a future preset time period is used as output data to train the neural network model.

[0010] In this embodiment of the application, for training a neural network model for predicting mud state, it is first necessary to acquire training data and collect and preprocess the training data. After completing the data preprocessing, feature construction and dimensionality reduction can be performed on the processed data to extract the key features of mud state changes over time. Then, the extracted key feature vectors are used as training data for the neural network model. After completing the training of the neural network model, the trained neural network model is deployed to achieve online prediction.

[0011] In one implementation of this application, the monitoring device includes at least one of a density sensor, a viscosity sensor, and a sand content sensor, and the state parameters include at least one of specific gravity, fluidity, and sand content. The state parameters of the mud are obtained through the sensors, including: The density sensor is used to obtain the density data of the mud in order to determine the specific gravity of the mud. And / or, obtain the viscosity data of the mud through the viscosity sensor to determine the fluidity of the mud; And / or, the sand content data of the mud is obtained through the sand content sensor to determine the sand content of the mud.

[0012] In this embodiment, a monitoring device network is constructed using multiple high-precision sensors. Each sensor not only possesses independent detection capabilities but also works collaboratively to achieve multi-dimensional acquisition of mud condition parameters. Through data fusion technology between sensors, single-parameter monitoring is transformed into multi-parameter comprehensive evaluation, reducing the risk of errors caused by the failure or interference of a single sensor and improving the comprehensiveness, reliability, and accuracy of mud condition monitoring.

[0013] In one implementation of this application, the adjustment device includes at least one of a raw material feeding device, a sand removal device, and a flow and pressure regulating device; the step of controlling the adjustment device to adjust the mud state based on the analysis results includes: If the predicted specific gravity of the mud does not meet the preset conditions, the amount of raw material fed into the device is controlled. And / or, if the sand content of the mud is predicted to be too high, control the desanding device to remove excess sand particles from the mud; And / or, if the predicted fluidity of the mud does not meet the preset conditions, the flow rate and / or pumping pressure of the mud are adjusted by the flow and pressure regulating device.

[0014] In this embodiment, when adjusting the monitoring equipment according to environmental parameters, the operating state of the monitoring equipment during detection can be adjusted, and the acquired signals can be post-processed. Specifically, adjusting the operating state of the monitoring equipment includes adjusting sensitivity or acquisition frequency, while processing the acquired signals can include filtering algorithms or compensation algorithms. This ensures that the monitoring equipment can select an appropriate adjustment method based on the actual environmental conditions, thereby ensuring the accuracy of the sensor data.

[0015] In one implementation of this application, the step of acquiring the state parameters of the mud through monitoring equipment further includes: Obtain the environmental parameters of the monitoring device; The monitoring equipment is adjusted based on the environmental parameters.

[0016] In this embodiment, since the environment during pile foundation construction is relatively complex and prone to adverse conditions such as vibration, low temperature, dust, and water seepage, existing monitoring technologies are prone to accuracy degradation or failure under these adverse conditions. In order to ensure stability under different environmental conditions, the environment around the monitoring equipment can be sensed. When environmental parameters such as temperature and vibration change, the monitoring equipment can be adjusted at the software or hardware level to reduce environmental interference with the sensors or to compensate for the detection data. This allows the monitoring equipment to adapt to different environmental conditions, reduces the impact on the accuracy of the monitoring equipment, and thus ensures the stability of the mud performance state under different environments.

[0017] In one implementation of this application, adjusting the monitoring device based on the environmental parameters includes: Adjust the sensitivity of the monitoring equipment according to the environmental parameters; And / or, adjust the acquisition frequency of the monitoring device according to the environmental parameters; And / or, perform preset processing on the collected signals of the monitoring device according to the environmental parameters.

[0018] In this embodiment, when adjusting the monitoring equipment according to environmental parameters, the operating state of the monitoring equipment during detection can be adjusted, and the acquired signals can be post-processed. Specifically, adjusting the operating state of the monitoring equipment includes adjusting sensitivity or acquisition frequency, while processing the acquired signals can include filtering algorithms or compensation algorithms. This ensures that the monitoring equipment can select an appropriate adjustment method based on the actual environmental conditions, thereby ensuring the accuracy of the sensor data.

[0019] On the other hand, embodiments of this application also provide a monitoring device for mud conditions, the device comprising: The acquisition module is used to acquire the state parameters of the mud through monitoring equipment; An analysis module is used to analyze the state parameters based on a neural network model; The adjustment module is used to control the adjustment equipment to adjust the state of the mud based on the analysis results.

[0020] This application embodiment can monitor the state of the mud in real time and predict the state of the mud through a neural network, thereby realizing intelligent control of the mud state. It can adjust the mud at the initial stage when abnormal mud performance occurs. Compared with the traditional manual inspection method, it does not rely on human experience and can adjust the mud state in advance, avoiding the delay caused by human intervention. It keeps the mud in the optimal state at all times, ensuring the mud's slag carrying capacity and wall stability, thereby ensuring the construction quality of the pile foundation and improving the safety and efficiency of construction.

[0021] On the other hand, embodiments of this application also provide a computer device, the device comprising: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform any of the mud state monitoring methods described above.

[0022] On the other hand, embodiments of this application also provide a non-volatile computer storage medium storing computer-executable instructions, wherein the computer, when executing the executable instructions, implements any of the mud state monitoring methods described above.

[0023] This application provides a method, device, computer equipment, and medium for monitoring the state of mud. Compared with the prior art, the embodiments of this application have the following beneficial technical effects: This application enables real-time monitoring of the mud's condition and prediction of its condition through neural networks, thereby achieving intelligent control of the mud's condition. It can adjust the mud at the initial stage of abnormal performance, which, compared with traditional manual inspection, does not rely on human experience and can adjust the mud's condition in advance, avoiding delays caused by manual intervention. This keeps the mud in its optimal state, ensuring its slag-carrying capacity and wall stability, thus guaranteeing the construction quality of the pile foundation and improving construction safety and efficiency. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 A flowchart illustrating a method for monitoring mud condition provided in an embodiment of this application; Figure 2 A flowchart illustrating step S120 in a mud state monitoring method provided in this application embodiment; Figure 3 A flowchart illustrating a method for monitoring mud conditions according to another embodiment of this application; Figure 4 A flowchart illustrating step S110 in a method for monitoring mud state provided in an embodiment of this application; Figure 5 A flowchart illustrating step S110 in a method for monitoring mud state according to another embodiment of this application; Figure 6 A flowchart illustrating step S116 in a method for monitoring mud state provided in an embodiment of this application; Figure 7 A flowchart illustrating step S130 in a method for monitoring mud state according to another embodiment of this application; Figure 8 A schematic diagram of the structure of a mud state monitoring device provided in an embodiment of this application; Figure 9 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0026] This application discloses a method, device, computer equipment, and medium for monitoring the state of mud, which solves the problems of existing technologies where manual inspection cannot monitor in real time, has large errors, and is difficult to handle in a timely manner.

[0027] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0028] Figure 1 This is a flowchart illustrating a method for monitoring mud conditions provided in an embodiment of this application.

[0029] The method for monitoring the state of mud involved in the embodiments of this application can be implemented by a terminal device, a server, or a combination of both. This application does not impose any special limitations on this. For ease of understanding and description, the following embodiments will be described in detail using a server as an example.

[0030] It should be noted that the server can be a single device or a system composed of multiple devices, i.e., a distributed server. This application does not make any specific limitations on this.

[0031] like Figure 1 As shown in the embodiment of this application, a method for monitoring the state of mud includes: Step S110: Obtain the state parameters of the mud through monitoring equipment.

[0032] Specifically, real-time acquisition of mud state parameters can be achieved through integrated sensors and other monitoring devices. These devices can be installed at key locations during mud slurry operations, transmitting real-time monitoring data to the processing unit via wireless or wired connections. The sampling frequency of mud parameters can be determined based on accuracy requirements, for example, it can be set to collect data more than 10 times per second, ensuring continuous real-time monitoring of mud state parameters and avoiding the problem of poor timeliness in traditional manual detection. The monitoring devices can include multiple and various types of sensors, enabling comprehensive perception and monitoring of different mud state parameters and reducing data acquisition errors.

[0033] Step S120: Analyze the state parameters based on the neural network model.

[0034] Specifically, after acquiring the state parameters of the mud, a neural network prediction model is used to analyze these parameters. This neural network model can be pre-trained for the mud state and stored locally or in the cloud. Specifically, through a neural network-based prediction algorithm, the changing trends of the acquired state parameters can be analyzed to predict the mud state over a future period, detect potential risks in the mud, and prevent abnormal mud performance, such as if the mud viscosity is too low or the sand content is too high. This allows for the notification of personnel for inspection or automatic adjustment.

[0035] Step S130: Adjust the mud state by controlling and adjusting the equipment according to the analysis results.

[0036] Specifically, after analyzing the mud state using a neural network model, corresponding actions can be taken based on the analysis results to adjust the mud's performance. This can be achieved by adjusting the mud's formula and composition. Furthermore, after the adjustment operation, the results can be fed back through monitoring equipment to evaluate the adjustment effect and dynamically adjust the next step. This establishes a closed-loop control system for mud state, achieving full automation from data acquisition to adjustment execution. It enables automatic sensing of mud state changes, calculation of the optimal adjustment scheme, and execution of adjustment operations, avoiding delays and errors caused by manual intervention and improving operational efficiency and accuracy.

[0037] In this embodiment, the state of the mud can be monitored in real time, and the state of the mud can be predicted through a neural network, thereby realizing intelligent control of the mud state. It can adjust the mud at the initial stage when abnormal mud performance occurs. Compared with the traditional manual inspection method, it does not rely on human experience and can adjust the mud state in advance, avoiding the delay caused by human intervention. It keeps the mud in the best state, ensuring the mud's slag carrying capacity and wall stability, thereby ensuring the construction quality of the pile foundation and improving the safety and efficiency of construction.

[0038] Figure 2 This is a flowchart illustrating step S120 of a mud state monitoring method provided in an embodiment of this application, as shown below. Figure 2 As shown, in one embodiment, step S120 may include: Step S121: Input the state parameters into the neural network model.

[0039] Step S122: Predict the state of mud in a future preset time period based on the output data of the neural network model.

[0040] Specifically, after inputting the mud state parameters acquired by the monitoring equipment into a pre-trained neural network model, the prediction algorithm based on the neural network can predict and analyze the future state of the mud. The neural network model evaluates the overall performance of the mud based on current and historical data, analyzes the changing trends of various mud state parameters, and combines this with soil characteristics such as soil density and water content to predict changes in the mud over a preset period. This allows for the detection of potential risks in the mud, such as decreased viscosity or excessive sand content, and provides early warning signals to notify personnel or activate automatic adjustment mechanisms for timely handling. Compared to traditional manual judgment, this reduces response time and improves construction safety.

[0041] Figure 3 A flowchart illustrating a method for monitoring mud conditions according to another embodiment of this application is shown below. Figure 3 As shown, in one embodiment, before step S120, the above method may further include: Step S101: Obtain historical state data of the mud and normalize the historical state data.

[0042] Specifically, for training a neural network model for predicting mud state, it is first necessary to acquire training data and perform data collection and preprocessing. First, acquire historical mud state data collected by monitoring equipment, and then normalize the collected historical state data to ensure that historical state data at different scales have equal weight in the neural network model. This avoids training bias caused by different data units and improves the accuracy of the neural network model.

[0043] Step S102: Based on the processed historical state data, extract the key feature vectors of mud state changes over time.

[0044] Specifically, after data preprocessing, feature construction and dimensionality reduction can be performed on the processed data. Key features of mud state changes over time, such as short-term mean, variance, and rate of change, can be extracted from historical state data. Principal component analysis (PCA) and other methods can then be used to reduce the dimensionality of high-dimensional data and extract the most representative feature vectors for subsequent training of neural network models.

[0045] Step S103: Use the key feature vector as input data and the predicted mud state for a future preset time period as output data to train the neural network model.

[0046] Specifically, the extracted key feature vectors are used as training data for the neural network model. The architecture of the neural network can be determined according to actual needs; for example, a multi-layer feedforward neural network or a recurrent neural network can be used. The structure of the neural network model can include an input layer, hidden layers, and an output layer. The input layer receives the processed key feature vectors, and at least 3 to 5 hidden layers are set, each using ReLU or tanh activation functions. In the recurrent neural network architecture, long short-term memory network units can be introduced to process time-series data to capture the temporal dependence of mud parameters. The output layer outputs the predicted values ​​of mud state, representing the expected change trends of various key mud parameters within a preset time period.

[0047] The neural network model uses mean squared error (MSE) as the loss function and employs the Adam or RMSProp optimizer to iteratively update the model parameters, ensuring both prediction accuracy and convergence speed. Simultaneously, an early stopping strategy is implemented to prevent overfitting and ensure the neural network model possesses good generalization ability. Furthermore, historical data and laboratory test data can be used for offline training of the neural network model. Cross-validation is used to determine hyperparameters such as the number of network layers, nodes, and learning rate. During training, the model's performance on the validation set is dynamically monitored to ensure that the error gradually decreases within an acceptable range.

[0048] After training the neural network model, it is deployed to achieve online prediction. To ensure the accuracy of the model's predictions, the predicted data can be compared with the actual monitoring data periodically, and the model parameters can be dynamically adjusted or the model can be retrained to ensure that the neural network model can adapt to the constantly changing construction site environment.

[0049] Figure 4 This is a flowchart illustrating step S110 of a method for monitoring mud state provided in an embodiment of this application. Figure 4 As shown, in one embodiment, the monitoring device includes at least one of a density sensor, a viscosity sensor, and a sand content sensor, and the state parameters include at least one of specific gravity, flowability, and sand content. Step S110 may include at least one of the following steps: Step S111: Obtain the density data of the mud using a density sensor to determine the specific gravity of the mud.

[0050] Specifically, excessively high or low mud density can cause the mud to lose its effective wall-protecting ability, thereby affecting the construction quality of the pile foundation. Therefore, it is necessary to monitor the mud density. Monitoring equipment can include density sensors, specifically hydrostatic density meters, which measure changes in mud density to determine the mud's specific gravity and consistency.

[0051] Step S112: Obtain the viscosity data of the mud using a viscosity sensor to determine the fluidity of the mud.

[0052] Specifically, excessively low mud viscosity leads to excessive mud fluidity, failing to effectively support the borehole wall; excessively high viscosity, on the other hand, may result in insufficient mud fluidity, affecting the mud's ability to carry slag. Therefore, it is necessary to monitor the mud viscosity. Monitoring equipment can include viscosity sensors, such as miniature resonant viscometers or rotor-type online viscometers. By measuring the mud viscosity using viscosity sensors, the fluidity of the mud during construction can be determined.

[0053] Step S113: Obtain the sand content data of the mud using a sand content sensor to determine the sand content of the mud.

[0054] Specifically, excessively high sand content in drilling mud can prevent it from carrying drill cuttings properly, increasing the risk of borehole collapse. Therefore, it is necessary to monitor the sand content of the drilling mud. Monitoring equipment can include sand content sensors, such as light scattering sensors, ultrasonic sensors, or laser-capacitive dual-mode sand content detectors. These sensors detect the content of solid particles in the drilling mud to determine its sand content.

[0055] In this embodiment, a monitoring device network is constructed using multiple high-precision sensors. Each sensor not only has independent detection capabilities but also works collaboratively to achieve multi-dimensional acquisition of mud condition parameters. Through data fusion technology between sensors, single-parameter monitoring is transformed into multi-parameter comprehensive evaluation, reducing the risk of errors caused by the failure or interference of a single sensor and improving the comprehensiveness, reliability, and accuracy of mud condition monitoring.

[0056] Figure 5 This is a flowchart illustrating step S110 of a method for monitoring mud state according to another embodiment of this application, as shown below. Figure 5 As shown, in one embodiment, step S110 may further include: Step S115: Obtain the environmental parameters of the monitoring equipment.

[0057] Step S116: Adjust the monitoring equipment based on environmental parameters.

[0058] Specifically, due to the complex environment during pile foundation construction, harsh conditions such as vibration, low temperature, dust, and water seepage are easily generated. Existing monitoring technologies are prone to accuracy degradation or failure under these harsh conditions. To ensure stability under different environmental conditions, the environment around the monitoring equipment can be sensed. When environmental parameters such as temperature and vibration change, the monitoring equipment can be adjusted at the software or hardware level to reduce environmental interference with the sensors or to compensate for the detection data. This allows the monitoring equipment to adapt to different environmental conditions, reduces the impact on the accuracy of the monitoring equipment, and thus ensures the stability of the mud performance under different environments.

[0059] Figure 6 This is a flowchart illustrating step S116 of a method for monitoring mud state provided in an embodiment of this application. Figure 6 As shown, in one embodiment, step S116 may include at least one of the following steps: Step S1161: Adjust the sensitivity of the monitoring equipment according to the environmental parameters.

[0060] Step S1162: Adjust the acquisition frequency of the monitoring equipment according to the environmental parameters.

[0061] Step S1163: Perform preset processing on the collected signals of the monitoring equipment according to the environmental parameters.

[0062] Specifically, when adjusting monitoring equipment based on environmental parameters, one can adjust the equipment's operating status during detection, or perform post-processing on the acquired signals. Adjusting the equipment's operating status includes adjusting sensitivity or sampling frequency, while signal processing can include filtering or compensation algorithms. This ensures that the monitoring equipment can select appropriate adjustment methods based on actual environmental conditions, thereby guaranteeing the accuracy of sensor data.

[0063] Furthermore, for example, when the mud is in a low-temperature environment, such as during winter construction, the fluidity and viscosity of the mud may change. After obtaining the low-temperature environmental parameters, the sensitivity of the viscosity sensor can be automatically adjusted, and the control strategy of the equipment can be modified and adjusted according to the mud characteristics under low-temperature conditions to ensure that the mud still maintains appropriate wall-protecting ability at low temperatures. Conversely, when the mud is in a vibrating environment, such as in earthquake-prone areas or construction sites with significant vibration, after obtaining the vibration environmental parameters, the data acquisition frequency of the sensor can be increased, and the acquired signals can be processed using enhanced signal filtering algorithms to avoid interference from vibration on the measurement of mud state parameters.

[0064] Furthermore, in other optional embodiments, the above method further includes: Interference prevention measures are activated based on environmental parameters.

[0065] Specifically, when the mud is in a strong electromagnetic interference environment, the anti-electromagnetic interference function can be activated to ensure that the monitoring equipment can work stably in a strong electromagnetic environment and avoid the electrical equipment at the construction site from affecting the sensor data.

[0066] Figure 7 This is a flowchart illustrating step S130 of a method for monitoring mud state provided in an embodiment of this application. Figure 7 As shown, in one embodiment, the adjusting device includes at least one of a raw material feeding device, a sand removal device, and a flow and pressure regulating device, and the above step S130 may include at least one of the following steps: Step S131: If the predicted specific gravity of the mud does not meet the preset conditions, control the amount of raw material fed into the feeding device.

[0067] Specifically, when neural network model analysis determines that the mud density has decreased and its specific gravity does not fall within the preset range, it indicates that the mud may be too thin and unable to effectively support the borehole wall or remove drill cuttings. In this case, the feedstock delivery device can be controlled to change the amount or proportion of mud components, thereby restoring the mud's specific gravity to the preset range. The feedstock delivery device can specifically be a bentonite replenishment device, which includes a hopper and a control pump. The control pump can control the delivery of a preset amount of bentonite according to instructions to adjust the mud's density and viscosity, ensuring that the mud has sufficient wall-supporting capacity during construction.

[0068] Step S132: If the sand content of the mud is predicted to be too high, control the desanding device to remove excess sand particles from the mud.

[0069] Specifically, when neural network model analysis determines that the sand content of the mud is too high, it indicates a decrease in the mud's slag-carrying capacity, thus affecting construction quality. At this point, a desanding device can be activated to remove excess sand particles from the mud, thereby restoring the sand content to a preset range. The desanding device can include ultrasonic vibration devices or mechanical screening devices, which can separate and discharge excess sand particles from the mud, restoring the mud's optimal slag-carrying capacity.

[0070] Step S133: If the predicted fluidity of the mud does not meet the preset conditions, adjust the flow rate and / or pumping pressure of the mud through the flow and pressure regulating device.

[0071] Specifically, when neural network model analysis determines that the mud viscosity has decreased and its fluidity does not meet the preset range, it indicates that the mud may be too thin or too thick. In this case, flow and pressure regulating devices can be used to adjust the mud flow rate and pumping pressure. These devices can include solenoid valves and pressure pumps, etc., to optimize the mud fluidity and ensure uniform flow during drilling. For example, if the mud is too thin, the pumping pressure or flow rate can be increased to ensure that the mud effectively carries away drill cuttings and maintains borehole stability.

[0072] In this embodiment, a precise mud control mechanism is introduced, which can control and adjust the equipment in real time to change the composition and state of the mud based on the analysis results of the neural network model. It can accurately calculate the timing of the adjustment operation and the amount of material to be added, avoiding the problems of untimely adjustment and waste caused by excessive material addition that are easy to occur in traditional manual adjustment. This effectively improves the efficiency of mud state adjustment and reduces adjustment costs.

[0073] In one embodiment, the above method may further include: In the event of a failure in the monitoring and / or adjustment equipment, the backup equipment shall be controlled to operate.

[0074] Specifically, to improve the stability of the adjustment process, redundant designs are adopted in key modules of both monitoring and adjustment equipment. For example, backup sensors are installed at important locations, backup processors are installed in control units, and dual drive control is implemented in the adjustment equipment. When some equipment fails, it can quickly switch to backup equipment to ensure uninterrupted overall control of mud condition monitoring. Simultaneously, multiple data verification mechanisms can be implemented through backup equipment to reduce errors and ensure accurate and reliable operation.

[0075] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide a mud state monitoring device, the structure of which is as follows: Figure 8 As shown.

[0076] Figure 8 This is a schematic diagram of the structure of a mud condition monitoring device provided in an embodiment of this application. Figure 8 As shown, the monitoring equipment for mud condition includes: The acquisition module 210 is used to acquire the state parameters of the mud through monitoring equipment; Analysis module 220 is used to analyze state parameters based on a neural network model; The adjustment module 230 is used to control the adjustment equipment to adjust the state of the mud based on the analysis results.

[0077] The aforementioned mud condition monitoring equipment can monitor the mud condition in real time and predict it through neural networks, thereby achieving intelligent control of the mud condition. It can adjust the mud condition at the initial stage when abnormal mud performance occurs. Compared with the traditional manual inspection method, it does not rely on human experience and can adjust the mud condition in advance, avoiding delays caused by human intervention. It keeps the mud in the optimal state, ensuring the mud's slag carrying capacity and wall stability, thereby guaranteeing the construction quality of the pile foundation and improving the safety and efficiency of construction.

[0078] It is understood that the above-mentioned mud state monitoring equipment can also be used to implement the mud state monitoring method in any of the above embodiments, and has corresponding functional modules.

[0079] Figure 9 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Figure 9 As shown, the device includes: At least one processor; And, a memory that is communicatively connected to at least one processor; The memory stores instructions that can be executed by at least one processor. When the instructions are executed by at least one processor, the method for monitoring the state of mud as described in any of the above embodiments is implemented.

[0080] In one embodiment of this application, when the processor executes the instructions, it can: acquire the state parameters of the mud through a monitoring device; analyze the state parameters based on a neural network model; and control the adjustment device to adjust the state of the mud according to the analysis results.

[0081] This application also provides a non-volatile computer storage medium storing computer-executable instructions, which, when executed by the computer, implement the mud state monitoring method as described in any of the above embodiments.

[0082] In one embodiment of this application, when the above instructions are executed by the processor, they can achieve the following: acquiring the state parameters of the mud through a monitoring device; analyzing the state parameters based on a neural network model; and controlling the adjustment device to adjust the state of the mud according to the analysis results.

[0083] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0084] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0086] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0090] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0091] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0092] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0093] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0094] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for monitoring the state of mud, characterized in that, The method includes: The state parameters of the mud are obtained through monitoring equipment; The state parameters are analyzed based on a neural network model; Based on the analysis results, the control and adjustment equipment is used to adjust the state of the mud.

2. The method for monitoring mud condition according to claim 1, characterized in that, The analysis of the state parameters based on the neural network model includes: The state parameters are input into the neural network model; The output data of the neural network model is used to predict the state of mud in a future preset time period.

3. The method for monitoring mud condition according to claim 1, characterized in that, Before the step of inputting the state parameters into the neural network model, the method further includes: Obtain historical state data of the mud, and normalize the historical state data; Based on the processed historical state data, key feature vectors of mud state changes over time are extracted. The key feature vectors are used as input data, and the predicted mud state for a future preset time period is used as output data to train the neural network model.

4. The method for monitoring mud condition according to claim 1, characterized in that, The monitoring device includes at least one of a density sensor, a viscosity sensor, and a sand content sensor. The state parameters include at least one of specific gravity, fluidity, and sand content. The state parameters of the mud obtained by the sensors include: The density sensor is used to obtain the density data of the mud in order to determine the specific gravity of the mud. And / or, obtain the viscosity data of the mud through the viscosity sensor to determine the fluidity of the mud; And / or, the sand content data of the mud is obtained through the sand content sensor to determine the sand content of the mud.

5. The method for monitoring mud condition according to claim 4, characterized in that, The adjustment equipment includes at least one of a raw material feeding device, a sand removal device, and a flow and pressure regulating device. The step of controlling the adjustment equipment to adjust the mud state based on the analysis results includes: If the predicted specific gravity of the mud does not meet the preset conditions, the amount of raw material fed into the device is controlled. And / or, if the sand content of the mud is predicted to be too high, control the desanding device to remove excess sand particles from the mud; And / or, if the predicted fluidity of the mud does not meet the preset conditions, the flow rate and / or pumping pressure of the mud are adjusted by the flow and pressure regulating device.

6. The method for monitoring mud condition according to claim 1, characterized in that, The acquisition of mud state parameters through monitoring equipment also includes: Obtain the environmental parameters of the monitoring device; The monitoring equipment is adjusted based on the environmental parameters.

7. The method for monitoring mud condition according to claim 6, characterized in that, Adjusting the monitoring equipment based on the environmental parameters includes: Adjust the sensitivity of the monitoring equipment according to the environmental parameters; And / or, adjust the acquisition frequency of the monitoring device according to the environmental parameters; And / or, perform preset processing on the collected signals of the monitoring device according to the environmental parameters.

8. A monitoring device for mud state, characterized in that, The device includes: The acquisition module is used to acquire the state parameters of the mud through monitoring equipment; An analysis module is used to analyze the state parameters based on a neural network model; The adjustment module is used to control the adjustment equipment to adjust the state of the mud based on the analysis results.

9. A computer device, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the mud state monitoring method as described in any one of claims 1-7.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer implements the method for monitoring the state of mud as described in any one of claims 1-7 when executing executable instructions.

Images