Foundation pit water pump water pumping intelligent control system and method based on Internet of Things

Abstract

The invention belongs to the technical field of foundation pit drainage, and aims to solve the problems that a traditional water pump starting and stopping mode is slow in response and low in error-tolerant rate and cannot meet the deep foundation pit construction requirement. The invention provides a foundation pit water pump water pumping intelligent control system and method based on the Internet of Things. A controller is used for constructing a double-guarantee mechanism; a foundation pit water pump pumping water level threshold value and a current threshold value are built in the controller, the current threshold value is updated in real time through a water level-current prediction model built in the controller and a seasonal factor, and the water level-current prediction model is used for obtaining a current prediction value of water pump load current based on the foundation pit water level depth; wherein the first guarantee mechanism is used for controlling start and stop of a water pump based on real-time foundation pit water level depth and a water level threshold value; and the second guarantee mechanism is used for controlling the start and stop of the water pump based on the real-time water pump load current, the current threshold and the phase sequence state. According to the invention, state monitoring and regulation and control integrated closed-loop management of the foundation pit water pumping control system can be realized.

Description

Technical Field

[0001] This invention belongs to the field of foundation pit drainage technology, specifically relating to an intelligent control system and method for foundation pit water pumping based on the Internet of Things. Background Technology

[0002] Due to the complexity of the geological and hydrological environment, the construction of foundation pits faces risks such as sudden surge of pressurized water and leakage of surrounding rock. It is necessary to combine geological data and meteorological information to predict water level changes, but traditional systems lack the ability to integrate and analyze multi-source data.

[0003] Traditional foundation pit drainage systems rely on manual inspection of water pump operation status to determine water level. For example, using a steel ruler water level gauge or a single current monitoring system can lead to problems such as delayed water level response, difficulty in monitoring phase loss faults, data loss in case of sudden power outages, and high risk of water pump idling / overload.

[0004] In existing technologies, single-phase current detection and phase sequence protection functions are often designed separately, and water level monitoring and pump control are mostly independent modules, lacking a collaborative decision-making mechanism. Furthermore, the adaptive control capability during pump start-up and shutdown is weak; most systems use fixed thresholds to control pump start-up and shutdown, failing to dynamically adjust the drainage rate based on water level changes (such as fluctuations and seasonal effects). This easily leads to over-pumping causing ground subsidence or insufficient drainage causing water accumulation. The operation and maintenance of enclosed spaces such as foundation pits are difficult, and equipment maintenance is inconvenient. Deep foundation pit construction faces the severe challenge of pressurized water risks. Traditional manual measurement and pump start-up / shutdown methods are slow and have low fault tolerance, failing to meet the safety and efficiency requirements of deep foundation pit construction. Summary of the Invention

[0005] In order to solve at least one of the above-mentioned technical problems in the prior art, the present invention provides an intelligent control system and method for foundation pit water pumping based on the Internet of Things.

[0006] The present invention is implemented using the following technical solution: an intelligent control system for foundation pit water pumping based on the Internet of Things, including a controller, a water pressure sensor, a current transformer, a phase loss and phase sequence detection module, a cloud-controlled intelligent circuit breaker, a wireless transceiver, and a multi-level power supply module. The water pressure sensor is used to collect the static pressure of the water level in the foundation pit and transmit it to the controller. The controller obtains the water level depth of the foundation pit based on the relationship between the static pressure of the water level and the water level depth. The current transformer is used to obtain the real-time water pump load current. The phase loss and phase sequence detection module is used to monitor the phase sequence status of the three-phase electricity. The controller is used to construct a dual protection mechanism. The controller has built-in water level threshold and current threshold for the foundation pit water pump. The current threshold is updated in real time through the built-in water level-current prediction model and seasonal factors. The water level-current prediction model is used to obtain the current prediction value of the water pump load current based on the foundation pit water level depth. The first protection mechanism is used to control the start and stop of the water pump based on the real-time foundation pit water level depth and water level threshold. The second protection mechanism is used to control the start and stop of the water pump based on the real-time water pump load current, current threshold and phase sequence status. The cloud-controlled intelligent circuit breaker is used to control the power supply of the water pump based on the phase loss power-off command of the controller; the wireless transceiver is used to transmit the status parameters of the water pump to the control room terminal; the multi-level power module is used to provide the required power to the controller, water pressure sensor, current transformer, phase loss and phase sequence detection module, cloud-controlled intelligent circuit breaker, and wireless transceiver.

[0007] Preferably, the controller and the wireless transceiver form a star-hierarchical hybrid network; wherein the controller serves as the central node in the first-level network of the star-hierarchical hybrid network; in the second-level network, the water pumps in the foundation pit are divided into N groups, each group has M nodes, and a relay node is designated within each group, and the number of water pumps in the foundation pit is N. M; The N groups of water pumps are divided into independent channels, and each group of water pumps uses a different channel.

[0008] Preferably, the controller chip is STM32F103, and the wireless transceiver model is CC1101; the controller drives the wireless transceiver through the SPI serial peripheral interface, and each relay node of the water pump group adds an LNA low-noise amplifier to the RF front end; the ordinary nodes adopt a dynamic power management strategy and control the sleep wake-up mechanism through a hardware timer, and enter a deep sleep mode during non-communication periods; the relay nodes adopt a dual power supply redundancy mode.

[0009] Preferably, the phase loss and phase sequence detection module uses a TC783A chip. The controller reads the phase sequence status through GPIO to perform phase loss detection and phase sequence detection of the three-phase power supply. When a phase loss is detected, a phase loss power-off command is output to the cloud-controlled intelligent circuit breaker. The circuit transformer is a single-phase current transformer used for B-phase current monitoring. The controller integrates an ADC to obtain the static pressure of the pit water level and the water pump load current.

[0010] Preferably, the decision model of the intelligent control system for foundation pit water pumping has four states: standby, operation, fault, and emergency power supply. In standby mode, the controller continuously monitors the pump start signal, and the controller display refreshes the power status. In operation mode, the controller's ADC samples the pump load current at intervals of Pms. If the current exceeds the threshold, it immediately switches to fault mode. At the same time, the phase loss and phase sequence detection module monitors in real time. If a phase is lost or the phase sequence is reversed, the interrupt pin is pulled high to trigger state transition. Meanwhile, the wireless transceiver uploads the pump status parameters to the control room terminal at intervals of Qms. In fault mode, the cloud-controlled intelligent circuit breaker is forcibly disconnected, the controller display flashes the fault code, and the status is locked until manual reset. In emergency power supply mode, when the main power supply of the multi-level power module is interrupted, it automatically switches to battery power and shuts down unnecessary peripherals, maintaining only the core functions.

[0011] Preferably, the multi-stage power module outputs 24V power to the water pressure sensor via a 380V external power supply through a transformer and an AD-DC conversion module, 12V power to the relay controlling the cloud-controlled intelligent circuit breaker, 5V power to the controller, current transformer, and wireless transceiver, and 3.7V power to the battery.

[0012] This invention also provides an intelligent control method for foundation pit water pumping based on the Internet of Things, comprising the following steps: interval Record a single data pair of pit water level depth and pump load current, and retain it. Data from the past day, and outlier filtering performed; Linear regression modeling, the expression for the linear regression model is: ,in This is the pump load current. This refers to the depth of the foundation pit water level. The slope The intercept; The objective function is to minimize the sum of the differences between the measured values ​​and the predicted values ​​of the pump load current in multiple sets. The model is trained using the pit water level depth and pump load current data to obtain the linear regression model corresponding to the optimal slope and intercept parameters. Obtain the real-time monitored water level depth in the foundation pit; The pump load current is calculated based on a trained linear regression model and pit water level depth data. The calculated pump load current time series data is then used to train an ARIMA model to generate future... The predicted current value of the pump load current is obtained, and the rate of change of the predicted current value of the pump load current is calculated by linear fitting. Define a seasonal factor and update the current threshold in real time based on the current prediction value, the seasonal factor, and the rate of change of the current prediction value of the pump load current. The pump start-up and shutdown are controlled based on real-time pit water level depth, real-time pump load current, water level threshold, and real-time updated current threshold.

[0013] Preferably, the step of defining the seasonal factor includes: The dry season and rainy season are divided according to the range of water level changes; The expression for the seasonal factor is defined as follows: And when At that time, it was the dry season; when The time is the rainy season; in the formula, This is the real-time water level depth in the foundation pit. , These are the upper and lower thresholds for the water level depth in the foundation pit, respectively.

[0014] Preferably, the formula for updating the current threshold in real time based on the predicted current value, seasonal factors, and the rate of change of the pump load current is as follows: In the formula, For current threshold, This is the predicted current value; The rate of change of the predicted value of the pump load current; when Greater than 1.2 When, hard protection is triggered; when Greater than ,and When the value is greater than 0, a trend warning is issued. This represents the real-time pump load current.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This application improves the energy efficiency of water pump systems by 3%-5% and reduces false alarm rate by 60% by accurately mapping the water level-current relationship and predicting trends in advance, thereby reducing ineffective operating time. By establishing a water level-current relationship model and combining it with a time-series ARIMA model for prediction, dynamic current threshold adjustment is achieved, avoiding idling or overload caused by traditional fixed thresholds. The current prediction model can predict load changes up to 2 hours in advance, reducing energy consumption spikes caused by frequent start-stop cycles.

[0016] In addition, the water level in the foundation pit, the current and status of the water pump are transmitted to the control terminal via a wireless transceiver, promoting the transformation from "manual intervention" to "cloud decision-making + local execution", and realizing the integrated closed-loop management of the foundation pit pumping control system status monitoring and control. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a system hardware block diagram of this application; Figure 2 This is a logical diagram of the system operation status of this application; Figure 3 This is a flowchart of the method in this application. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] It should be noted that the structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportional relationships, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should fall within the scope of the technical content disclosed in the present invention. It should be noted that in this specification, relational terms such as "first" and "second" are only used to distinguish one entity from several other entities, and do not necessarily require or imply any actual relationship or order between these entities.

[0021] This invention provides an embodiment: like Figure 1 , Figure 2 As shown, an IoT-based intelligent control system for foundation pit water pumping includes a controller, a water pressure sensor, a current transformer, a phase loss and phase sequence detection module, a cloud-controlled intelligent circuit breaker, a wireless transceiver, and a multi-stage power supply module. The water pressure sensor collects the static pressure of the foundation pit water level and transmits it to the controller. The controller obtains the foundation pit water level depth based on the relationship between the static pressure and the water level depth. The current transformer obtains the real-time pump load current. The phase loss and phase sequence detection module monitors the phase sequence status of the three-phase power supply. The controller is used to construct a dual protection mechanism. The controller has built-in water level threshold and current threshold for the foundation pit water pump. The current threshold is updated in real time through the built-in water level-current prediction model and seasonal factors. The water level-current prediction model is used to obtain the current prediction value of the water pump load current based on the foundation pit water level depth. The first protection mechanism is used to control the start and stop of the water pump based on the real-time foundation pit water level depth and water level threshold. The second protection mechanism is used to control the start and stop of the water pump based on the real-time water pump load current, current threshold and phase sequence status. The cloud-controlled intelligent circuit breaker is used to control the power supply of the water pump based on the phase loss power-off command of the controller. The model of the cloud-controlled intelligent circuit breaker is Mini Cloud Control ZJSB9-125Z. The wireless transceiver is used to transmit the status parameters of the water pump to the control room terminal. The multi-stage power module is used to provide the required power to the controller, water pressure sensor, current transformer, phase loss and phase sequence detection module, cloud-controlled intelligent circuit breaker, and wireless transceiver.

[0022] In this embodiment, the controller and the wireless transceiver form a star-hierarchical hybrid network. The scheme achieves reliable networking of multiple nodes while ensuring real-time performance through packet channel multiplexing and hierarchical relay. The measured packet loss rate is illustrated using 50 nodes as an example. In the first-level network of the star-hierarchical hybrid network, the controller acts as the central node, equipped with a high-gain omnidirectional antenna. In the second-level network, the 50 water pumps in the pit are divided into 5 groups, each with 10 nodes, and a designated relay node within each group. The 433MHz frequency band is used, divided into 5 independent channels (1MHz apart). Each group of water pumps uses a different channel to avoid co-channel interference.

[0023] The controller chip is STM32F103, and the wireless transceiver model is CC1101. The controller drives the wireless transceiver through the SPI serial peripheral interface. Each relay node of the water pump group adds an LNA low-noise amplifier to the RF front end. The ordinary nodes adopt a dynamic power management strategy and control the sleep wake-up mechanism through a hardware timer (the working cycle is set to 1%). During non-communication periods, they enter a deep sleep mode, which reduces the average operating current to the microamp level. The relay nodes adopt a dual power supply redundancy mode to ensure the continuous and stable operation of critical nodes.

[0024] The system employs a Time Division Multiple Access (TDMA) mechanism, allocating a fixed time slot for each node to upload data. This TDMA scheme uses a hierarchical scheduling architecture; the T0 time slot is used for the central node to broadcast synchronization frames, ensuring all nodes can synchronize to the same time base. Synchronization frame broadcasts occur every 50 milliseconds. Time slots T1-T10 enable orderly access for nodes within the group, with each node having a 200ms upload duration. This means each node has a 200ms time window to upload its data. Synchronization frames use BPSK modulation, while data frames use GMSK modulation to improve spectral efficiency.

[0025] The data packet structure includes: Preamble: 1-byte synchronization header, used for frame synchronization and signal detection; Group ID: 1-byte identifier of the group to which the node belongs (groups 0-255); Data type: 1-byte to distinguish data categories (e.g., 0x01 for sensor data, 0x02 for heartbeat packets); Payload: 12 bytes of valid data, including: current value (2 bytes), water level value (4 bytes), fault code (2 bytes), and reserved field (4 bytes for expansion); CRC: 2-byte cyclic redundancy check; Data fragmentation transmission + ACK confirmation mechanism.

[0026] Data transmission status: Initialization; Initialization --> Sleep: Configuration complete; Sleep --> Data acquisition: Timed wake-up / interrupt trigger; Data acquisition --> Communication transmission: Packaging data; Communication transmission --> Fault handling: Anomaly detection; Fault handling --> Sleep: Recovery complete. This state transition logic enables full parameter monitoring of the water pump status, supporting remote start / stop and fault early warning.

[0027] In this embodiment, the phase loss and phase sequence detection module uses a TC783A chip. The controller reads the phase sequence status through GPIO to perform phase loss detection and phase sequence detection of the three-phase power supply. When a phase loss is detected, a phase loss power-off command is output to the cloud-controlled intelligent circuit breaker. The circuit transformer is a single-phase current transformer used for B-phase current monitoring and calculating the effective value based on the RMS algorithm. The controller integrates an ADC to obtain the static pressure of the pit water level and the water pump load current.

[0028] The decision-making model of the intelligent control system for foundation pit water pumping has four states: standby, operation, fault, and emergency power supply. In standby mode, the controller continuously monitors the pump start signal, and the controller display refreshes the power status. In operation mode, the controller's ADC samples the pump load current at intervals of Pms. If the current exceeds the threshold, it immediately switches to fault mode. At the same time, the phase loss and phase sequence detection module monitors in real time. If a phase is lost or the phase sequence is reversed, the interrupt pin is pulled high to trigger a state transition. Simultaneously, the wireless transceiver uploads the pump status parameters to the control room terminal at intervals of Qms. In fault mode, the cloud-controlled intelligent circuit breaker is forcibly disconnected, the controller display flashes a fault code, and the status is locked until manually reset. In emergency power supply mode, when the main power supply of the multi-stage power module is interrupted, it automatically switches to battery power and shuts down unnecessary peripherals, maintaining only the core functions.

[0029] The multi-stage power module outputs 24V from a 380V external power supply via a transformer and an AD-DC converter to the water pressure sensor, 12V to the relay controlling the cloud-controlled intelligent circuit breaker, 5V to the controller, current transformer, and wireless transceiver, and 3.7V to power the battery. In the event of a main power failure, the system automatically switches: AC-DC module shuts down → battery voltage is regulated by an LDO → maintaining control system standby time ≥48 hours.

[0030] Firstly, analysis of the response speeds of the water pressure sensor and the current transformer reveals that the water pressure sensor (water level detection) has a significantly faster response speed than the current transformer. This is because the water pressure sensor's delay comes from ADC conversion and temperature compensation; the current transformer's delay stems from the requirement to sample the entire cycle: a minimum 20ms delay (for a 50Hz system), and the need for harmonic analysis and filtering to eliminate harmonic interference. Considering the pump's operating efficiency and energy consumption, a hybrid control architecture combining water level control and current protection is adopted.

[0031] like Figure 3 As shown, the present invention also provides an intelligent control method for foundation pit water pumping based on the Internet of Things, comprising the following steps: interval Record a single data pair of pit water level depth and pump load current, and retain it. Data from the past day, and outlier filtering performed; Linear regression modeling, the expression for the linear regression model is: ,in This is the pump load current. This refers to the depth of the foundation pit water level. The slope The intercept; The objective function is to minimize the sum of the differences between the measured values ​​and the predicted values ​​of the pump load current in multiple sets. The model is trained using the pit water level depth and pump load current data to obtain the linear regression model corresponding to the optimal slope and intercept parameters. Obtain the real-time monitored water level depth in the foundation pit; The pump load current is calculated based on a trained linear regression model and pit water level depth data. The calculated pump load current time series data is then used to train an ARIMA model to generate future... The predicted current value of the pump load current is obtained, and the rate of change of the predicted current value of the pump load current is calculated by linear fitting. Define a seasonal factor and update the current threshold in real time based on the current prediction value, the seasonal factor, and the rate of change of the current prediction value of the pump load current. The pump start-up and shutdown are controlled based on real-time pit water level depth, real-time pump load current, water level threshold, and real-time updated current threshold. In this embodiment, the data pairs of pit water level depth and pump load current are recorded every 10 minutes, and the data for 7 days are retained. Outlier filtering, water level range verification (0.5m-5m), and current range verification (rated current ±30%) are performed.

[0032] In this embodiment, the objective function is: In the formula, , For the first Data pairs of pit water level depth and pump load current.

[0033] Solving the equation yields: ,in, .

[0034] In this embodiment, the ARIMA model is applied to predict the future. The invention uses an ARIMA(2,1,2) model to train the model, obtains the model using `model.fit()`, and applies the ARIMA model for prediction to generate future values. Predicted current value of the water pump load current.

[0035] First, an ARIMA(2,1,2) model was trained using the calculated time-series data of the pump load current, with the model initialized to order=(2,1,2). During data preprocessing, the training and test sets were divided in an 8:2 ratio, and the last 20% of the data was retained to verify the model's accuracy.

[0036] During model training, `model.fit()` automatically performs maximum likelihood estimation to optimize parameters. The output summary includes AIC / BIC metrics for comparing model performance. An outlier handling module is also used to improve prediction accuracy, perform current prediction, and linearly fit the trend slope.

[0037] Generate the predicted current value of the pump load current for the next n steps. And a 95% confidence interval. The predicted curve reflects the current trend and fluctuation range. Output model summary and error index, MSE assesses the deviation between predicted and actual values.

[0038] In this embodiment, the steps for defining the seasonal factor include: The dry season and rainy season are divided according to the magnitude of water level changes; the expression for the seasonal factor is defined as: And when At that time, it was the dry season; when The time is the rainy season; in the formula, This is the real-time water level depth in the foundation pit. = , These are the upper and lower thresholds for the water level depth in the foundation pit, respectively.

[0039] In this embodiment, the formula for updating the current threshold in real time based on the rate of change of the predicted current value, the seasonal factor, and the pump load current is as follows: In the formula, For current threshold, This is the predicted current value; The rate of change of the predicted value of the pump load current; when Greater than 1.2 When, hard protection is triggered; when Greater than ,and When the value is greater than 0, a trend warning is issued. This represents the real-time pump load current.

[0040] Simultaneously, through an online update mechanism and incremental learning, the model is fine-tuned every 2 hours using new data. The above algorithm can achieve: automatically increasing the start-up threshold by 10-15% during the rainy season, predicting current surges 5-8 minutes in advance, and maintaining a false alarm rate of <3%.

[0041] This invention is the first to integrate the TC783A phase sequence protection chip with current transformer data to achieve three-dimensional fault diagnosis based on "water level-current-phase sequence". In addition, this application can automatically adjust the pump start-stop threshold (such as automatically increasing the pumping frequency during the rainy season). The intelligent start-stop algorithm based on current trend prediction is an automated control method that combines real-time current monitoring and prediction models. Its core lies in analyzing the dynamic change characteristics of the pump operating current to achieve fault prediction and energy efficiency optimization.

[0042] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent control system for foundation pit water pumping based on the Internet of Things, characterized in that: It includes a controller, a water pressure sensor, a current transformer, a phase loss and phase sequence detection module, a cloud-controlled intelligent circuit breaker, a wireless transceiver, and a multi-stage power supply module. The water pressure sensor is used to collect the static pressure of the water level in the foundation pit and transmit it to the controller. The controller obtains the water level depth of the foundation pit based on the relationship between the static pressure of the water level and the water level depth. The current transformer is used to obtain the real-time water pump load current. The phase loss and phase sequence detection module is used to monitor the phase sequence status of the three-phase electricity. The controller is used to construct a dual protection mechanism. The controller has built-in water level threshold and current threshold for the foundation pit water pump. The current threshold is updated in real time through the built-in water level-current prediction model and seasonal factors. The water level-current prediction model is used to obtain the current prediction value of the water pump load current based on the foundation pit water level depth. The first protection mechanism is used to control the start and stop of the water pump based on the real-time foundation pit water level depth and water level threshold. The second protection mechanism is used to control the start and stop of the water pump based on the real-time water pump load current, current threshold and phase sequence status. The cloud-controlled intelligent circuit breaker is used to control the power supply of the water pump based on the phase loss power-off command of the controller; the wireless transceiver is used to transmit the status parameters of the water pump to the control room terminal; the multi-level power module is used to provide the required power to the controller, water pressure sensor, current transformer, phase loss and phase sequence detection module, cloud-controlled intelligent circuit breaker, and wireless transceiver.

2. The intelligent control system for foundation pit water pumping based on the Internet of Things as described in claim 1, characterized in that: The controller and wireless transceiver form a star-hierarchical hybrid network; in the first-level network of the star-hierarchical hybrid network, the controller acts as the central node; in the second-level network, the water pumps in the foundation pit are divided into N groups, each group has M nodes, and a relay node is designated within each group. The number of water pumps in the foundation pit is N. The M and N groups of water pumps are divided into independent channels, and each group of water pumps uses a different channel.

3. The intelligent control system for foundation pit water pumping based on the Internet of Things as described in claim 2, characterized in that: The controller chip is STM32F103, and the wireless transceiver model is CC1101. The controller drives the wireless transceiver through the SPI serial peripheral interface. Each relay node of the water pump group adds an LNA low-noise amplifier to the RF front end. The ordinary nodes adopt a dynamic power management strategy and control the sleep wake-up mechanism through a hardware timer to enter a deep sleep mode during non-communication periods. The relay nodes adopt a dual power supply redundancy mode.

4. The intelligent control system for foundation pit water pumping based on the Internet of Things as described in claim 3, characterized in that: The phase loss and phase sequence detection module uses the TC783A chip. The controller reads the phase sequence status through GPIO to perform phase loss detection and phase sequence detection of the three-phase power supply. When a phase loss is detected, it outputs a phase loss power-off command to the cloud-controlled intelligent circuit breaker. The circuit transformer is a single-phase current transformer used for B-phase current monitoring. The controller integrates an ADC to obtain the static pressure of the pit water level and the water pump load current.

5. The intelligent control system for foundation pit water pumping based on the Internet of Things as described in claim 4, characterized in that: The decision-making model of the intelligent control system for foundation pit water pumping has four states: standby, operation, fault, and emergency power supply. In standby mode, the controller continuously monitors the pump start signal, and the controller display refreshes the power status. In operation mode, the controller's ADC samples the pump load current at intervals of Pms. If the current exceeds the threshold, it immediately switches to fault mode. At the same time, the phase loss and phase sequence detection module monitors in real time. If a phase is lost or the phase sequence is reversed, the interrupt pin is pulled high to trigger a state transition. Simultaneously, the wireless transceiver uploads the pump status parameters to the control room terminal at intervals of Qms. In fault mode, the cloud-controlled intelligent circuit breaker is forcibly disconnected, the controller display flashes a fault code, and the status is locked until manually reset. In emergency power supply mode, when the main power supply of the multi-stage power module is interrupted, it automatically switches to battery power and shuts down unnecessary peripherals, maintaining only the core functions.

6. The intelligent control system for foundation pit water pumping based on the Internet of Things as described in claim 1, characterized in that: The multi-stage power module outputs 24V power to the water pressure sensor via a 380V external power supply through a transformer and an AD-DC conversion module, 12V power to the relay controlling the cloud-controlled intelligent circuit breaker, 5V power to the controller, current transformer, and wireless transceiver, and 3.7V power to the battery.

7. An intelligent control method for foundation pit pumping based on the Internet of Things (IoT), relying on the intelligent control system for foundation pit pumping based on the IoT as described in any one of claims 1 to 6, characterized in that, Includes the following steps: interval Record a single data pair of pit water level depth and pump load current, and retain it. Data from the past day, and outlier filtering performed; Linear regression modeling, the expression for the linear regression model is: ,in This is the pump load current. This refers to the depth of the foundation pit water level. The slope The intercept; The objective function is to minimize the sum of the differences between the measured values ​​and the predicted values ​​of the pump load current in multiple sets. The model is trained using the pit water level depth and pump load current data to obtain the linear regression model corresponding to the optimal slope and intercept parameters. Obtain the real-time monitored water level depth in the foundation pit; The pump load current is calculated based on a trained linear regression model and pit water level depth data. The calculated pump load current time series data is then used to train an ARIMA model to generate future... The predicted current value of the pump load current is obtained, and the rate of change of the predicted current value of the pump load current is calculated by linear fitting. Define a seasonal factor and update the current threshold in real time based on the current prediction value, the seasonal factor, and the rate of change of the current prediction value of the pump load current. The pump start-up and shutdown are controlled based on real-time pit water level depth, real-time pump load current, water level threshold, and real-time updated current threshold.

8. The intelligent control method for foundation pit water pumping based on the Internet of Things according to claim 7, characterized in that: The steps to define seasonal factors include: The dry season and rainy season are divided according to the range of water level changes; The expression for the seasonal factor is defined as follows: And when At that time, it was the dry season; when The time is the rainy season; in the formula, This is the real-time water level depth in the foundation pit. , These are the upper and lower thresholds for the water level depth in the foundation pit, respectively.

9. The intelligent control method for foundation pit water pumping based on the Internet of Things as described in claim 8, characterized in that: The formula for updating the current threshold in real time based on the rate of change of the predicted current value, seasonal factor, and pump load current is as follows: In the formula, For current threshold, This is the predicted current value; The rate of change of the predicted value of the pump load current; when Greater than 1.2 When, hard protection is triggered; when Greater than ,and When the value is greater than 0, a trend warning is issued. This represents the real-time pump load current.

Images