Wireless remote detection control system applied to oilfield sewage treatment

Abstract

The invention provides a wireless remote detection control system applied to oilfield sewage treatment, belongs to the field of oilfield sewage treatment detection control, and is used for solving the problems of insufficient detection precision, unstable communication, high energy consumption and weak environmental adaptability in related technologies. The system comprises an environment adaptation enhancement module, a data processing module, a multi-modal communication module, an edge-cloud collaborative decision-making module and a self-adaptive energy management module, and data full-link fidelity optimization, redundant communication, distributed decision-making and dynamic energy management are realized through multi-module collaboration. And the detection precision, the communication continuity, the decision-making timeliness and the environmental adaptability are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of oilfield sewage treatment detection control, and particularly relates to a wireless remote detection control system applied to oilfield sewage treatment. BACKGROUND

[0002] Oilfield sewage treatment is an important link of oilfield production, and real-time monitoring of water quality parameters is needed to ensure treatment effect. At present, the industry mostly uses traditional wired monitoring systems or simple wireless sensor networks to realize basic data acquisition and transmission.

[0003] In the prior art, the data processing of the detection system mostly relies on single sensor calibration and simple weighted fusion, which is difficult to cope with parameter coupling interference in high turbidity and strong corrosion environments, resulting in insufficient detection accuracy. At the same time, the communication mode is mostly single-mode transmission, which is easy to cause signal interruption in remote oilfield areas, affecting data continuity.

[0004] In addition, the existing system has a single energy management mode, mostly relies on battery power supply, and has limited endurance; the environmental adaptability is weak, the sensor is easily affected by electromagnetic interference and material corrosion, and it is difficult to meet the long-term stable operation demand, and the above defects restrict the intelligent upgrading of oilfield sewage treatment. SUMMARY

[0005] The present application provides a wireless remote detection control system applied to oilfield sewage treatment, which can improve detection accuracy, enhance environmental adaptability and reduce energy consumption through full-link optimization and collaborative mechanism.

[0006] The present application provides a wireless remote detection control system applied to oilfield sewage treatment, comprising: a data processing module for full-link fidelity optimization of detection data; a multi-modal communication module supporting redundant transmission of at least two communication protocols; an edge-cloud collaborative decision module realizing distributed decision of multiple nodes; and a self-adaptive energy management module combining environmental energy collection and dynamic energy consumption control.

[0007] By adopting the above technical solutions, the integration optimization of data processing, communication, decision and energy management is realized through multi-module collaboration, solving the problems of insufficient accuracy, unstable communication and high energy consumption of traditional systems, and improving the overall performance of oilfield sewage treatment monitoring.

[0008] Further, the data processing module comprises: a source calibration unit configured to calibrate the initial data of the sensor based on a multi-physical field dynamic compensation model; and an intelligent agent fusion unit adopting a Bayesian fusion algorithm based on causal relationship mining to realize multi-source data fusion.

[0009] By adopting the technical scheme, the original data precision and multi-source data consistency are improved through multi-physical field compensation and causal fusion, and the influence of environmental interference on the detection result is reduced.

[0010] Further, the source calibration unit further comprises: a chaotic prediction subunit that dynamically compensates sensor drift using a nonlinear prediction model; and a phase space reconstruction module that constructs a data feature space based on a maximum Lyapunov index.

[0011] By adopting the technical scheme, the long-term drift of the sensor is accurately compensated through nonlinear drift prediction and feature space reconstruction, the calibration period is prolonged, and the data stability is improved.

[0012] Further, the intelligent agent fusion unit further comprises: a causal consistency verification module that detects data anomalies through a parent-child node cooperative mechanism; and a dynamic weighted fusion module that adaptively adjusts the fusion weight according to the noise memory characteristic.

[0013] By adopting the technical scheme, the abnormal data is accurately identified and the fusion strategy is optimized through causal verification and dynamic weighting, and the reliability of multi-source data fusion is improved.

[0014] Further, the multi-modal communication module comprises: a dual-mode communication link that simultaneously supports LoRa wireless transmission and 4G network backup; and a data semantic distillation unit that extracts decision key features for lightweight transmission.

[0015] By adopting the technical scheme, the continuity of communication is ensured while the data transmission amount is reduced through dual-mode communication and feature distillation, the real-time performance is improved, and the energy consumption is reduced.

[0016] Further, the edge-cloud collaborative decision-making module comprises: an edge autonomous response unit that independently executes control instructions in an emergency; and a complex network synchronization module that iteratively realizes node state consistency based on coupling strength.

[0017] By adopting the technical scheme, the emergency processing speed and node cooperation accuracy are improved through edge autonomous response and network synchronization, and the timeliness and consistency of system decision-making are ensured.

[0018] Further, the adaptive energy management module comprises: a hybrid power supply unit that integrates a solar cell and a micro hydroelectric generator; and an energy-transmission matching module that dynamically switches communication strategies according to real-time power generation.

[0019] By adopting the technical scheme, the energy utilization efficiency is improved through hybrid power supply and dynamic matching, the device endurance is prolonged, and the power supply problem in remote areas is solved.

[0020] Further, the adaptive energy management module further comprises: a nested computing power scaling unit, which activates computing resources on demand based on a master node-subnode hierarchy; and a self-organizing energy Mesh network, which supports energy assistance and load balancing between adjacent nodes.

[0021] By adopting the above technical solution, the energy distribution is optimized through computing power scaling and energy assistance, local node energy overload is avoided, and the overall endurance of the system is improved.

[0022] Further, the system further comprises an environment adaptation enhancement module, which comprises: a gradient distribution sensor array, which densely deploys multiple types of sensors in high turbidity areas; and a composite protective shell, which adopts a preset protection level and a corrosion-resistant material.

[0023] By adopting the above technical solution, the adaptability of the sensor to complex environments is improved through gradient distribution and composite protection, and the comprehensiveness of data acquisition and the durability of equipment are ensured.

[0024] Further, the environment adaptation enhancement module further comprises: an electromagnetic shielding and signal filtering unit, which attenuates external electromagnetic interference of a preset intensity; and a heterogeneous redundant detection module, which fuses electrochemical and spectral detection data for complementary verification.

[0025] By adopting the above technical solution, the influence of external interference is reduced and the data redundancy is improved through electromagnetic shielding and heterogeneous verification, thereby ensuring the stability and reliability of the detection result.

[0026] In summary, the present application at least has the following beneficial effects:

[0027] 1. A full-link optimized detection control system is provided, which improves the accuracy and stability of oilfield wastewater treatment monitoring;

[0028] 2. Through multi-modal communication and collaborative decision-making, the continuity of data transmission and the timeliness of decision-making are ensured;

[0029] 3. Through adaptive energy management and environmental enhancement design, the endurance of the equipment is prolonged and the adaptability to complex environments is improved.

[0030] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0031] The above and other features, advantages, and aspects of the embodiments of the present application will become more apparent by describing in detail the following detailed description in conjunction with the accompanying drawings. In the drawings, the same or similar reference numerals indicate the same or similar elements, in which:

[0032] Figure 1 A principle diagram of a wireless remote detection control system applied to oilfield sewage treatment in the embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0034] In addition, the term “and / or” in this document only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character “ / ” in this document generally represents an “or” relationship between the front and rear associated objects.

[0035] The present application provides a wireless remote detection control system applied to oilfield sewage treatment, which improves detection accuracy through full-link optimization, guarantees data continuity through multi-modal communication, prolongs endurance through adaptive energy management, meets complex working conditions through strong environmental adaptability, and helps sewage treatment intelligentization.

[0036] The embodiment of the present application discloses a wireless remote detection control system applied to oilfield sewage treatment.

[0037] Figure 1 A principle diagram of a wireless remote detection control system applied to oilfield sewage treatment in the embodiment of the present application is shown.

[0038] Reference Figure 1 The system includes a data processing module, a multi-modal communication module, an edge-cloud collaborative decision-making module, an adaptive energy management module, and an environmental adaptation enhancement module.

[0039] The data processing module is configured to perform full-link fidelity optimization on the detection data. The full-link optimization process starts from sensor raw data collection, and high-fidelity data is formed after multi-dimensional calibration, multi-source fusion, and noise reduction processing, providing reliable input for subsequent decision-making.

[0040] The data processing module includes a source calibration unit and an intelligent agent fusion unit. The source calibration unit is configured to calibrate the initial data of the sensor based on a multi-physical field dynamic compensation model, specifically through composite compensation of temperature, pressure, and electromagnetic interference: the temperature compensation term is wherein is the temperature coefficient, Real-time temperature, Calibration temperature; pressure compensation term is , Pressure coefficient, Real-time pressure, Standard atmospheric pressure, Turbidity value; electromagnetic interference compensation term is Electromagnetic intensity, Signal-to-noise ratio, final calibration value is The agent fusion unit realizes multi-source data fusion by using a Bayesian fusion algorithm based on causal relationship mining, and improves the physical logic of fusion by constructing a causal network between parameters.

[0041] The source calibration unit further includes a chaotic prediction subunit and a phase space reconstruction module. The chaotic prediction subunit uses a nonlinear prediction model to dynamically compensate for sensor drift. First, the maximum Lyapunov exponent is calculated to verify the chaotic characteristics of the drift data, and then a chaotic LSTM model is used to output future drift prediction values , combined with the calibration value to obtain a pre-calibration result . The phase space reconstruction module constructs a data feature space based on the maximum Lyapunov exponent, determines the delay time and embedding dimension by using the C-C method, and forms a phase space vector to provide input features for chaotic prediction.

[0042] The agent fusion unit further includes a causal consistency verification module and a dynamic weighted fusion module. The causal consistency verification module detects data anomalies through a parent-child node collaborative mechanism. Based on the causal graph mined by the PC algorithm, when a child node parameter is abnormal, it needs to verify whether its parent node is also abnormal, i.e. Only when , otherwise it is determined as invalid data. The dynamic weighted fusion module adaptively adjusts the fusion weight according to the noise memory feature. The weight calculation formula is , where is the conditional probability, is the sensor reliability, is the noise rate, is the spatial distance, and the optimal fusion of multi-source data is realized through dynamic weight distribution, is the noise rate weight coefficient (artificially set, value range 0.1-0.5).

[0043] The data processing module further includes a fractional order noise reduction unit for noise reduction processing of the fused data. The fractional order noise reduction unit uses a fusion algorithm of fractional order Kalman filter and fractional order wavelet transform. The state equation of the fractional order Kalman filter is wherein is Caputo fractional derivative is state transition matrix, is control input matrix, is process noise; fractional wavelet transform adopts mother function in fractional derivative form is fractional order, and noise memory index dynamically adjusts the fusion weight of the two , and the final denoising result is wherein is the fractional Kalman filtering result, is the fractional wavelet transform result.

[0044] The multi-modal communication module supports redundant transmission of at least two communication protocols; the redundant transmission mechanism is realized by dynamic switching of protocol priority, when the signal strength of the main communication link (LoRa) is lower than the preset threshold, it is automatically switched to the backup link (4G), ensuring the continuity of data transmission, and the switching judgment is based on wherein is the LoRa received signal strength, is the bit error rate, is the communication switching weight coefficient (artificially set, value range 0.6-0.8).

[0045] The multi-modal communication module includes a dual-mode communication link and a data semantic distillation unit, the dual-mode communication link simultaneously supports LoRa wireless transmission and 4G network backup, the LoRa link adopts an improved AODV routing algorithm, and the routing discovery frequency is dynamically adjusted to is the network congestion degree, is the congestion influence coefficient (artificially set, value range 0.2-0.4), ensuring efficient communication under low power consumption; the 4G link is activated as an emergency backup when the LoRa link is interrupted for more than a preset time, ensuring that critical data is not lost; the data semantic distillation unit extracts key features for lightweight transmission, and constructs a "semantic importance" evaluation model wherein Impact is the influence degree of the feature on the decision, is the rarity of the feature, only core features higher than the threshold are transmitted, reducing the amount of transmitted data while retaining the key information required for decision-making.

[0046] ​The edge-cloud collaborative decision module realizes distributed decision of multiple levels of nodes; the distributed decision is realized through two-dimensional division of "task sensitivity-response timeliness", the edge node focuses on real-time decision with low delay demand (such as pollution early warning), the cloud is responsible for global optimization decision (such as long-term trend prediction and strategy adjustment), and the two interact with key data in real time through an encryption protocol to form a "local response-global optimization" closed loop.

[0047] The edge-cloud collaborative decision module includes an edge autonomous response unit and a complex network synchronization module. The edge autonomous response unit independently executes control instructions in emergency situations, and the emergency situation determination is based on task sensitivity calculation: , wherein is the decay rate of detection accuracy over time, is the growth rate of energy consumption with the number of nodes, energy consumption growth weight (all are artificially set, with a value range of 0.3-0.7), when (high sensitivity threshold), the edge node directly activates the control instruction (such as adjusting the flow of the dosing pump) without waiting for cloud feedback; the complex network synchronization module realizes node state consistency based on coupling strength iteration, and the coupling strength , wherein is the spatial distance between nodes and , and is the correlation coefficient of the data of the two, is the distance attenuation coefficient, and the state consistency is realized through the iteration formula , is the synchronization gain, which ensures that the data of each node is consistent within the allowed error range, supporting the unity of global decision.

[0048] The adaptive energy management module combines environmental energy harvesting and dynamic energy consumption control; the module dynamically allocates energy harvesting and consumption by monitoring environmental parameters such as solar irradiance and wastewater flow rate in real time, forming a closed-loop management of "harvesting-storage-distribution-consumption", and the core indicator is the matching degree of energy remaining and predicted energy consumption .

[0049] The adaptive energy management module includes a hybrid power supply unit and an energy-transmission matching module. The hybrid power supply unit integrates solar cells and micro hydro generators, and realizes energy integration through a maximum power point tracking (MPPT) controller. The total power generation , wherein , are the conversion efficiencies of solar and hydroelectricity, , are the instantaneous power generation; the energy-transmission matching module dynamically switches the communication strategy according to the real-time power generation, and sets the power threshold ,when Transmission mode, transmitting full characteristics; when Real-time transmission core features; when Only abnormal flags are transmitted at any time, so that energy consumption and supply are dynamically balanced.

[0050] The adaptive energy management module further includes nested computing power scaling units and a self-organizing energy mesh network. The nested computing power scaling units activate computing resources on demand based on a master-child node hierarchy, and the task complexity is evaluated as Complexity. ,in This is the second derivative of concentration (reflecting the degree of drastic change). The number of abnormal parameters, when Complexity Time-based wake-up of child nodes (high-performance DSP), automatic sleep after completion of computation, reducing standby power consumption; self-organizing energy mesh network supports energy mutual assistance and load balancing among neighboring nodes, with energy priority evaluation as Priority. , Assess the urgency of node tasks. For nodes with remaining power, high-priority nodes obtain energy from neighboring high-power nodes via magnetic resonance coupling technology. Routing is based on an improved AODV algorithm, incorporating node energy status into the weights. This avoids energy-depleted nodes becoming forwarding bottlenecks, achieving energy "peak shaving and valley filling".

[0051] The environmental adaptation enhancement module includes a gradient-distribution sensor array and a composite protective housing. The gradient-distribution sensor array densely deploys multiple types of sensors in high-turbidity areas, specifically by dividing the area through real-time turbidity monitoring and setting turbidity thresholds. ,when When identified as a high-turbidity area, the deployment density is as follows: Calculation, where For reference density (e.g.) indivual), A proportionality coefficient (ranging from 1.5 to 2.0) ensures that the data acquisition density in high-turbidity areas is 2 to 3 times that in low-turbidity areas. Multiple sensor types, including pH, COD, and turbidity sensors, are used to form complementary parameter monitoring. The composite protective shell uses a preset protection level and corrosion-resistant materials. The preset protection level is IP68, capable of withstanding continuous immersion at a depth of 3 meters. The corrosion-resistant material is 316L stainless steel. corrosion resistance coefficient Much lower than ordinary carbon steel ( It can effectively resist oilfield wastewater. Corrosion, corrosion rate satisfy ,in For the concentration of corrosive medium, For time, For material constant (316L Year).

[0052] The environmental adaptation enhancement module further includes an electromagnetic shielding and signal filtering unit and a heterogeneous redundancy detection module. The electromagnetic shielding and signal filtering unit attenuates external electromagnetic interference of a preset intensity. The shielding effectiveness is calculated as , where is the reflection loss is the free space impedance, is the shielding material impedance, is the absorption loss is the shielding layer thickness, is the skin depth, is the multiple reflection correction , which overall ensures the attenuation of electromagnetic interference in the frequency band ; the filtering unit uses a second-order Butterworth filter with a cutoff frequency as the main interference frequency, as the cutoff frequency coefficient), further suppressing residual interference. The heterogeneous redundancy detection module fuses electrochemical and spectral detection data for complementary verification, with a fusion formula of , where is the electrochemical detection value (largely affected by temperature), is the spectral detection value (temperature interference resistant), with a confidence ( is the real-time temperature, is the calibration temperature, is the temperature influence coefficient), , when any detection unit fails, the other unit temporarily fills in based on the historical mapping model is the mapping function trained through 100,000 samples) to ensure detection continuity.

[0053] The initial data of the sensor is calibrated through a multi-physical field dynamic compensation model, which can offset the coupling effects of environmental factors such as temperature, pressure, and electromagnetic interference on the detection value. Combined with a chaotic LSTM nonlinear prediction model for dynamic compensation of sensor drift, it can reduce systematic errors in long-term use and provide high-fidelity raw data for subsequent data processing. Based on the Bayesian fusion algorithm for causal relationship mining, through parent node-child node collaborative verification and dynamic weighting, abnormal data can be filtered and the consistency of multi-source data can be improved. After processing long memory noise through a fractional calculus denoising model, random interference is further reduced, ensuring the overall accuracy and stability of the data link.

[0054] The multi-modal communication module can avoid the signal interruption risk of single communication mode in complex oilfield environment through the redundant transmission of LoRa and 4G dual-mode link, and can reduce the invalid data transmission amount by cooperating with the data semantic distillation to extract the key features of decision-making, while ensuring data continuity and reducing communication energy consumption, thereby providing stable data interaction support for edge-cloud collaborative decision-making.

[0055] In the edge-cloud collaborative decision-making mechanism, the edge node realizes autonomous response to emergency based on task sensitivity, which can shorten the decision delay of critical scenarios, and the cloud realizes node state consistency based on coupling strength iteration through the complex network synchronization module, which can ensure the unity of global decision-making. The combination of the two forms a closed loop of "local rapid response-global optimization control", which improves the adaptation ability of the system to dynamic working conditions.

[0056] The adaptive energy management module can break through the limitations of single energy supply through the mixed power supply of solar and hydroelectric power, and the energy-transmission matching module can dynamically switch communication strategies according to power generation and activate computing resources on demand through the nested computing resource scaling unit, which can realize the dynamic balance of energy consumption and supply, and can avoid system paralysis caused by local energy depletion through the node energy assistance of self-organizing energy Mesh network, thereby significantly prolonging the device endurance cycle.

[0057] The environmental adaptation enhancement module can ensure the monitoring coverage density in complex water quality areas through the gradient distribution sensor array in high turbidity areas, and the combination of IP68 protection level and corrosion-resistant materials can resist sewage corrosion and immersion, and the electromagnetic shielding and signal filtering unit can attenuate strong electromagnetic interference, and the heterogeneous redundant detection module can improve the detection reliability in abnormal working conditions through the complementary verification of electrochemical and spectral data, so that the system can maintain long-term stable operation in the harsh environment of high turbidity, strong corrosion and multiple interference in oilfields.

[0058] In summary, the technical means of each module through the logical chain of "data fidelity-communication reliability-decision-making in time-energy sustainability-environmental adaptation" synergistic effect, ultimately realizes the overall improvement of the oilfield sewage treatment wireless remote detection and control system in precision, continuity, stability and adaptability.

[0059] The above description is only the preferred embodiment of the present application and the explanation of the technical principles applied. Those skilled in the art should understand that the disclosure range involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and also covers other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features disclosed in the present application (but not limited to) with similar functions to form a technical solution.

Claims

1. A wireless remote monitoring and control system for oilfield wastewater treatment, characterized in that, include: The data processing module is used to optimize the fidelity of the detection data throughout the entire process. A multimodal communication module that supports redundant transmission of at least two communication protocols; The edge-cloud collaborative decision-making module enables distributed decision-making across multiple levels of nodes; The adaptive energy management module combines environmental energy harvesting with dynamic energy consumption control.

2. The system according to claim 1, characterized in that, The data processing module includes: The source calibration unit is configured to calibrate the initial sensor data based on a multiphysics dynamic compensation model; The intelligent agent fusion unit uses a Bayesian fusion algorithm based on causal relationship mining to achieve multi-source data fusion.

3. The system according to claim 2, characterized in that, The source calibration unit further includes: The chaotic prediction subunit uses a nonlinear prediction model to dynamically compensate for sensor drift. The phase space reconstruction module constructs a data feature space based on the maximum Lyapunov exponent.

4. The system according to claim 2, characterized in that, The intelligent agent fusion unit further includes: The causal consistency verification module detects data anomalies through a parent-child node collaboration mechanism. The dynamic weighted fusion module adaptively adjusts the fusion weights based on the noise memory characteristics.

5. The system according to claim 1, characterized in that, The multimodal communication module includes: Dual-mode communication link, supporting both LoRa wireless transmission and 4G network backup; The data semantic distillation unit extracts key decision features for lightweight transmission.

6. The system according to claim 1, characterized in that, The edge-cloud collaborative decision-making module includes: Edge autonomous response units can independently execute control commands in emergency situations; The complex network synchronization module achieves node state consistency based on iterative coupling strength.

7. The system according to claim 1, characterized in that, The adaptive energy management module includes: Hybrid power supply unit, integrating solar cells and miniature hydroelectric generator; The energy-transmission matching module dynamically switches communication strategies based on real-time power generation.

8. The system according to claim 7, characterized in that, The adaptive energy management module further includes: Nested computing power scaling units activate computing resources on demand based on a master-child node hierarchy; Self-organizing energy mesh networks support energy sharing and load balancing among neighboring nodes.

9. The system according to claim 1, characterized in that, The system also includes an environmental adaptation enhancement module, comprising: Gradient-distribution sensor arrays are used to densely deploy multiple types of sensors in high-turbidity areas. The composite protective shell uses a preset protection level and corrosion-resistant materials.

10. The system according to claim 9, characterized in that, The environmental adaptation enhancement module further includes: Electromagnetic shielding and signal filtering unit attenuates external electromagnetic interference of a preset intensity; A heterogeneous redundant detection module integrates electrochemical and spectroscopic detection data for complementary verification.

Images